1 files changed, 153 insertions, 53 deletions

diff --git a/midx.c b/midx.c
index 4a01583fe8..837b46b2af 100644
--- a/midx.c
+++ b/midx.c
@@ -57,15 +57,15 @@ const unsigned char *get_midx_checksum(struct multi_pack_index *m)
 	return m->data + m->data_len - the_hash_algo->rawsz;
 }
 
-char *get_midx_filename(const char *object_dir)
+void get_midx_filename(struct strbuf *out, const char *object_dir)
 {
-	return xstrfmt("%s/pack/multi-pack-index", object_dir);
+	strbuf_addf(out, "%s/pack/multi-pack-index", object_dir);
 }
 
-char *get_midx_rev_filename(struct multi_pack_index *m)
+void get_midx_rev_filename(struct strbuf *out, struct multi_pack_index *m)
 {
-	return xstrfmt("%s/pack/multi-pack-index-%s.rev",
-		       m->object_dir, hash_to_hex(get_midx_checksum(m)));
+	get_midx_filename(out, m->object_dir);
+	strbuf_addf(out, "-%s.rev", hash_to_hex(get_midx_checksum(m)));
 }
 
 static int midx_read_oid_fanout(const unsigned char *chunk_start,
@@ -89,28 +89,30 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local
 	size_t midx_size;
 	void *midx_map = NULL;
 	uint32_t hash_version;
-	char *midx_name = get_midx_filename(object_dir);
+	struct strbuf midx_name = STRBUF_INIT;
 	uint32_t i;
 	const char *cur_pack_name;
 	struct chunkfile *cf = NULL;
 
-	fd = git_open(midx_name);
+	get_midx_filename(&midx_name, object_dir);
+
+	fd = git_open(midx_name.buf);
 
 	if (fd < 0)
 		goto cleanup_fail;
 	if (fstat(fd, &st)) {
-		error_errno(_("failed to read %s"), midx_name);
+		error_errno(_("failed to read %s"), midx_name.buf);
 		goto cleanup_fail;
 	}
 
 	midx_size = xsize_t(st.st_size);
 
 	if (midx_size < MIDX_MIN_SIZE) {
-		error(_("multi-pack-index file %s is too small"), midx_name);
+		error(_("multi-pack-index file %s is too small"), midx_name.buf);
 		goto cleanup_fail;
 	}
 
-	FREE_AND_NULL(midx_name);
+	strbuf_release(&midx_name);
 
 	midx_map = xmmap(NULL, midx_size, PROT_READ, MAP_PRIVATE, fd, 0);
 	close(fd);
@@ -179,12 +181,13 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local
 	trace2_data_intmax("midx", the_repository, "load/num_packs", m->num_packs);
 	trace2_data_intmax("midx", the_repository, "load/num_objects", m->num_objects);
 
+	free_chunkfile(cf);
 	return m;
 
 cleanup_fail:
 	free(m);
-	free(midx_name);
-	free(cf);
+	strbuf_release(&midx_name);
+	free_chunkfile(cf);
 	if (midx_map)
 		munmap(midx_map, midx_size);
 	if (0 <= fd)
@@ -460,6 +463,8 @@ struct write_midx_context {
 	uint32_t num_large_offsets;
 
 	int preferred_pack_idx;
+
+	struct string_list *to_include;
 };
 
 static void add_pack_to_midx(const char *full_path, size_t full_path_len,
@@ -469,8 +474,26 @@ static void add_pack_to_midx(const char *full_path, size_t full_path_len,
 
 	if (ends_with(file_name, ".idx")) {
 		display_progress(ctx->progress, ++ctx->pack_paths_checked);
+		/*
+		 * Note that at most one of ctx->m and ctx->to_include are set,
+		 * so we are testing midx_contains_pack() and
+		 * string_list_has_string() independently (guarded by the
+		 * appropriate NULL checks).
+		 *
+		 * We could support passing to_include while reusing an existing
+		 * MIDX, but don't currently since the reuse process drags
+		 * forward all packs from an existing MIDX (without checking
+		 * whether or not they appear in the to_include list).
+		 *
+		 * If we added support for that, these next two conditional
+		 * should be performed independently (likely checking
+		 * to_include before the existing MIDX).
+		 */
 		if (ctx->m && midx_contains_pack(ctx->m, file_name))
 			return;
+		else if (ctx->to_include &&
+			 !string_list_has_string(ctx->to_include, file_name))
+			return;
 
 		ALLOC_GROW(ctx->info, ctx->nr + 1, ctx->alloc);
 
@@ -948,7 +971,43 @@ static void bitmap_show_commit(struct commit *commit, void *_data)
 	data->commits[data->commits_nr++] = commit;
 }
 
+static int read_refs_snapshot(const char *refs_snapshot,
+			      struct rev_info *revs)
+{
+	struct strbuf buf = STRBUF_INIT;
+	struct object_id oid;
+	FILE *f = xfopen(refs_snapshot, "r");
+
+	while (strbuf_getline(&buf, f) != EOF) {
+		struct object *object;
+		int preferred = 0;
+		char *hex = buf.buf;
+		const char *end = NULL;
+
+		if (buf.len && *buf.buf == '+') {
+			preferred = 1;
+			hex = &buf.buf[1];
+		}
+
+		if (parse_oid_hex(hex, &oid, &end) < 0)
+			die(_("could not parse line: %s"), buf.buf);
+		if (*end)
+			die(_("malformed line: %s"), buf.buf);
+
+		object = parse_object_or_die(&oid, NULL);
+		if (preferred)
+			object->flags |= NEEDS_BITMAP;
+
+		add_pending_object(revs, object, "");
+	}
+
+	fclose(f);
+	strbuf_release(&buf);
+	return 0;
+}
+
 static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr_p,
+						    const char *refs_snapshot,
 						    struct write_midx_context *ctx)
 {
 	struct rev_info revs;
@@ -957,8 +1016,12 @@ static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr
 	cb.ctx = ctx;
 
 	repo_init_revisions(the_repository, &revs, NULL);
-	setup_revisions(0, NULL, &revs, NULL);
-	for_each_ref(add_ref_to_pending, &revs);
+	if (refs_snapshot) {
+		read_refs_snapshot(refs_snapshot, &revs);
+	} else {
+		setup_revisions(0, NULL, &revs, NULL);
+		for_each_ref(add_ref_to_pending, &revs);
+	}
 
 	/*
 	 * Skipping promisor objects here is intentional, since it only excludes
@@ -987,6 +1050,7 @@ static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr
 
 static int write_midx_bitmap(char *midx_name, unsigned char *midx_hash,
 			     struct write_midx_context *ctx,
+			     const char *refs_snapshot,
 			     unsigned flags)
 {
 	struct packing_data pdata;
@@ -1002,7 +1066,7 @@ static int write_midx_bitmap(char *midx_name, unsigned char *midx_hash,
 
 	prepare_midx_packing_data(&pdata, ctx);
 
-	commits = find_commits_for_midx_bitmap(&commits_nr, ctx);
+	commits = find_commits_for_midx_bitmap(&commits_nr, refs_snapshot, ctx);
 
 	/*
 	 * Build the MIDX-order index based on pdata.objects (which is already
@@ -1046,36 +1110,52 @@ cleanup:
 	return ret;
 }
 
+static struct multi_pack_index *lookup_multi_pack_index(struct repository *r,
+							const char *object_dir)
+{
+	struct multi_pack_index *cur;
+
+	/* Ensure the given object_dir is local, or a known alternate. */
+	find_odb(r, object_dir);
+
+	for (cur = get_multi_pack_index(r); cur; cur = cur->next) {
+		if (!strcmp(object_dir, cur->object_dir))
+			return cur;
+	}
+
+	return NULL;
+}
+
 static int write_midx_internal(const char *object_dir,
+			       struct string_list *packs_to_include,
 			       struct string_list *packs_to_drop,
 			       const char *preferred_pack_name,
+			       const char *refs_snapshot,
 			       unsigned flags)
 {
-	char *midx_name;
+	struct strbuf midx_name = STRBUF_INIT;
 	unsigned char midx_hash[GIT_MAX_RAWSZ];
 	uint32_t i;
 	struct hashfile *f = NULL;
 	struct lock_file lk;
 	struct write_midx_context ctx = { 0 };
-	struct multi_pack_index *cur;
 	int pack_name_concat_len = 0;
 	int dropped_packs = 0;
 	int result = 0;
 	struct chunkfile *cf;
 
-	/* Ensure the given object_dir is local, or a known alternate. */
-	find_odb(the_repository, object_dir);
-
-	midx_name = get_midx_filename(object_dir);
-	if (safe_create_leading_directories(midx_name))
+	get_midx_filename(&midx_name, object_dir);
+	if (safe_create_leading_directories(midx_name.buf))
 		die_errno(_("unable to create leading directories of %s"),
-			  midx_name);
+			  midx_name.buf);
 
-	for (cur = get_multi_pack_index(the_repository); cur; cur = cur->next) {
-		if (!strcmp(object_dir, cur->object_dir)) {
-			ctx.m = cur;
-			break;
-		}
+	if (!packs_to_include) {
+		/*
+		 * Only reference an existing MIDX when not filtering which
+		 * packs to include, since all packs and objects are copied
+		 * blindly from an existing MIDX if one is present.
+		 */
+		ctx.m = lookup_multi_pack_index(the_repository, object_dir);
 	}
 
 	if (ctx.m && !midx_checksum_valid(ctx.m)) {
@@ -1125,10 +1205,13 @@ static int write_midx_internal(const char *object_dir,
 	else
 		ctx.progress = NULL;
 
+	ctx.to_include = packs_to_include;
+
 	for_each_file_in_pack_dir(object_dir, add_pack_to_midx, &ctx);
 	stop_progress(&ctx.progress);
 
-	if (ctx.m && ctx.nr == ctx.m->num_packs && !packs_to_drop) {
+	if ((ctx.m && ctx.nr == ctx.m->num_packs) &&
+	    !(packs_to_include || packs_to_drop)) {
 		struct bitmap_index *bitmap_git;
 		int bitmap_exists;
 		int want_bitmap = flags & MIDX_WRITE_BITMAP;
@@ -1293,7 +1376,7 @@ static int write_midx_internal(const char *object_dir,
 		pack_name_concat_len += MIDX_CHUNK_ALIGNMENT -
 					(pack_name_concat_len % MIDX_CHUNK_ALIGNMENT);
 
-	hold_lock_file_for_update(&lk, midx_name, LOCK_DIE_ON_ERROR);
+	hold_lock_file_for_update(&lk, midx_name.buf, LOCK_DIE_ON_ERROR);
 	f = hashfd(get_lock_file_fd(&lk), get_lock_file_path(&lk));
 
 	if (ctx.nr - dropped_packs == 0) {
@@ -1330,9 +1413,10 @@ static int write_midx_internal(const char *object_dir,
 		ctx.pack_order = midx_pack_order(&ctx);
 
 	if (flags & MIDX_WRITE_REV_INDEX)
-		write_midx_reverse_index(midx_name, midx_hash, &ctx);
+		write_midx_reverse_index(midx_name.buf, midx_hash, &ctx);
 	if (flags & MIDX_WRITE_BITMAP) {
-		if (write_midx_bitmap(midx_name, midx_hash, &ctx, flags) < 0) {
+		if (write_midx_bitmap(midx_name.buf, midx_hash, &ctx,
+				      refs_snapshot, flags) < 0) {
 			error(_("could not write multi-pack bitmap"));
 			result = 1;
 			goto cleanup;
@@ -1342,7 +1426,8 @@ static int write_midx_internal(const char *object_dir,
 	if (ctx.m)
 		close_object_store(the_repository->objects);
 
-	commit_lock_file(&lk);
+	if (commit_lock_file(&lk) < 0)
+		die_errno(_("could not write multi-pack-index"));
 
 	clear_midx_files_ext(object_dir, ".bitmap", midx_hash);
 	clear_midx_files_ext(object_dir, ".rev", midx_hash);
@@ -1360,16 +1445,28 @@ cleanup:
 	free(ctx.entries);
 	free(ctx.pack_perm);
 	free(ctx.pack_order);
-	free(midx_name);
+	strbuf_release(&midx_name);
 
 	return result;
 }
 
 int write_midx_file(const char *object_dir,
 		    const char *preferred_pack_name,
+		    const char *refs_snapshot,
 		    unsigned flags)
 {
-	return write_midx_internal(object_dir, NULL, preferred_pack_name, flags);
+	return write_midx_internal(object_dir, NULL, NULL, preferred_pack_name,
+				   refs_snapshot, flags);
+}
+
+int write_midx_file_only(const char *object_dir,
+			 struct string_list *packs_to_include,
+			 const char *preferred_pack_name,
+			 const char *refs_snapshot,
+			 unsigned flags)
+{
+	return write_midx_internal(object_dir, packs_to_include, NULL,
+				   preferred_pack_name, refs_snapshot, flags);
 }
 
 struct clear_midx_data {
@@ -1412,20 +1509,22 @@ static void clear_midx_files_ext(const char *object_dir, const char *ext,
 
 void clear_midx_file(struct repository *r)
 {
-	char *midx = get_midx_filename(r->objects->odb->path);
+	struct strbuf midx = STRBUF_INIT;
+
+	get_midx_filename(&midx, r->objects->odb->path);
 
 	if (r->objects && r->objects->multi_pack_index) {
 		close_midx(r->objects->multi_pack_index);
 		r->objects->multi_pack_index = NULL;
 	}
 
-	if (remove_path(midx))
-		die(_("failed to clear multi-pack-index at %s"), midx);
+	if (remove_path(midx.buf))
+		die(_("failed to clear multi-pack-index at %s"), midx.buf);
 
 	clear_midx_files_ext(r->objects->odb->path, ".bitmap", NULL);
 	clear_midx_files_ext(r->objects->odb->path, ".rev", NULL);
 
-	free(midx);
+	strbuf_release(&midx);
 }
 
 static int verify_midx_error;
@@ -1478,12 +1577,15 @@ int verify_midx_file(struct repository *r, const char *object_dir, unsigned flag
 	if (!m) {
 		int result = 0;
 		struct stat sb;
-		char *filename = get_midx_filename(object_dir);
-		if (!stat(filename, &sb)) {
+		struct strbuf filename = STRBUF_INIT;
+
+		get_midx_filename(&filename, object_dir);
+
+		if (!stat(filename.buf, &sb)) {
 			error(_("multi-pack-index file exists, but failed to parse"));
 			result = 1;
 		}
-		free(filename);
+		strbuf_release(&filename);
 		return result;
 	}
 
@@ -1516,7 +1618,7 @@ int verify_midx_file(struct repository *r, const char *object_dir, unsigned flag
 		 * Remaining tests assume that we have objects, so we can
 		 * return here.
 		 */
-		return verify_midx_error;
+		goto cleanup;
 	}
 
 	if (flags & MIDX_PROGRESS)
@@ -1594,7 +1696,9 @@ int verify_midx_file(struct repository *r, const char *object_dir, unsigned flag
 	}
 	stop_progress(&progress);
 
+cleanup:
 	free(pairs);
+	close_midx(m);
 
 	return verify_midx_error;
 }
@@ -1603,7 +1707,7 @@ int expire_midx_packs(struct repository *r, const char *object_dir, unsigned fla
 {
 	uint32_t i, *count, result = 0;
 	struct string_list packs_to_drop = STRING_LIST_INIT_DUP;
-	struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
+	struct multi_pack_index *m = lookup_multi_pack_index(r, object_dir);
 	struct progress *progress = NULL;
 
 	if (!m)
@@ -1648,12 +1752,11 @@ int expire_midx_packs(struct repository *r, const char *object_dir, unsigned fla
 
 	free(count);
 
-	if (packs_to_drop.nr) {
-		result = write_midx_internal(object_dir, &packs_to_drop, NULL, flags);
-		m = NULL;
-	}
+	if (packs_to_drop.nr)
+		result = write_midx_internal(object_dir, NULL, &packs_to_drop, NULL, NULL, flags);
 
 	string_list_clear(&packs_to_drop, 0);
+
 	return result;
 }
 
@@ -1769,7 +1872,7 @@ int midx_repack(struct repository *r, const char *object_dir, size_t batch_size,
 	struct child_process cmd = CHILD_PROCESS_INIT;
 	FILE *cmd_in;
 	struct strbuf base_name = STRBUF_INIT;
-	struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
+	struct multi_pack_index *m = lookup_multi_pack_index(r, object_dir);
 
 	/*
 	 * When updating the default for these configuration
@@ -1840,12 +1943,9 @@ int midx_repack(struct repository *r, const char *object_dir, size_t batch_size,
 		goto cleanup;
 	}
 
-	result = write_midx_internal(object_dir, NULL, NULL, flags);
-	m = NULL;
+	result = write_midx_internal(object_dir, NULL, NULL, NULL, NULL, flags);
 
 cleanup:
-	if (m)
-		close_midx(m);
 	free(include_pack);
 	return result;
 }