Merge branch 'tb/repack-write-midx'

"git repack" has been taught to generate multi-pack reachability
bitmaps.

* tb/repack-write-midx:
  test-read-midx: fix leak of bitmap_index struct
  builtin/repack.c: pass `--refs-snapshot` when writing bitmaps
  builtin/repack.c: make largest pack preferred
  builtin/repack.c: support writing a MIDX while repacking
  builtin/repack.c: extract showing progress to a variable
  builtin/repack.c: rename variables that deal with non-kept packs
  builtin/repack.c: keep track of existing packs unconditionally
  midx: preliminary support for `--refs-snapshot`
  builtin/multi-pack-index.c: support `--stdin-packs` mode
  midx: expose `write_midx_file_only()` publicly

Documentation/git-multi-pack-index.txt

@@ -45,6 +45,25 @@ write::
 
 	--[no-]bitmap::
 		Control whether or not a multi-pack bitmap is written.
+
+	--stdin-packs::
+		Write a multi-pack index containing only the set of
+		line-delimited pack index basenames provided over stdin.
+
+	--refs-snapshot=<path>::
+		With `--bitmap`, optionally specify a file which
+		contains a "refs snapshot" taken prior to repacking.
++
+A reference snapshot is composed of line-delimited OIDs corresponding to
+the reference tips, usually taken by `git repack` prior to generating a
+new pack. A line may optionally start with a `+` character to indicate
+that the reference which corresponds to that OID is "preferred" (see
+linkgit:git-config[1]'s `pack.preferBitmapTips`.)
++
+The file given at `<path>` is expected to be readable, and can contain
+duplicates. (If a given OID is given more than once, it is marked as
+preferred if at least one instance of it begins with the special `+`
+marker).
 --
 
 verify::

Documentation/git-repack.txt

@@ -9,7 +9,7 @@ git-repack - Pack unpacked objects in a repository
 SYNOPSIS
 --------
 [verse]
-'git repack' [-a] [-A] [-d] [-f] [-F] [-l] [-n] [-q] [-b] [--window=<n>] [--depth=<n>] [--threads=<n>] [--keep-pack=<pack-name>]
+'git repack' [-a] [-A] [-d] [-f] [-F] [-l] [-n] [-q] [-b] [-m] [--window=<n>] [--depth=<n>] [--threads=<n>] [--keep-pack=<pack-name>] [--write-midx]
 
 DESCRIPTION
 -----------
@@ -128,10 +128,11 @@ depth is 4095.
 -b::
 --write-bitmap-index::
 	Write a reachability bitmap index as part of the repack. This
-	only makes sense when used with `-a` or `-A`, as the bitmaps
+	only makes sense when used with `-a`, `-A` or `-m`, as the bitmaps
 	must be able to refer to all reachable objects. This option
-	overrides the setting of `repack.writeBitmaps`.  This option
-	has no effect if multiple packfiles are created.
+	overrides the setting of `repack.writeBitmaps`. This option
+	has no effect if multiple packfiles are created, unless writing a
+	MIDX (in which case a multi-pack bitmap is created).
 
 --pack-kept-objects::
 	Include objects in `.keep` files when repacking.  Note that we
@@ -189,6 +190,15 @@ this "roll-up", without respect to their reachability. This is subject
 to change in the future. This option (implying a drastically different
 repack mode) is not guaranteed to work with all other combinations of
 option to `git repack`.
++
+When writing a multi-pack bitmap, `git repack` selects the largest resulting
+pack as the preferred pack for object selection by the MIDX (see
+linkgit:git-multi-pack-index[1]).
+
+-m::
+--write-midx::
+	Write a multi-pack index (see linkgit:git-multi-pack-index[1])
+	containing the non-redundant packs.
 
 CONFIGURATION
 -------------

builtin/multi-pack-index.c

@@ -7,7 +7,8 @@
 #include "object-store.h"
 
 #define BUILTIN_MIDX_WRITE_USAGE \
-	N_("git multi-pack-index [<options>] write [--preferred-pack=<pack>]")
+	N_("git multi-pack-index [<options>] write [--preferred-pack=<pack>]" \
+	   "[--refs-snapshot=<path>]")
 
 #define BUILTIN_MIDX_VERIFY_USAGE \
 	N_("git multi-pack-index [<options>] verify")
@@ -45,8 +46,10 @@ static char const * const builtin_multi_pack_index_usage[] = {
 static struct opts_multi_pack_index {
 	const char *object_dir;
 	const char *preferred_pack;
+	const char *refs_snapshot;
 	unsigned long batch_size;
 	unsigned flags;
+	int stdin_packs;
 } opts;
 
 static struct option common_opts[] = {
@@ -77,6 +80,16 @@ static int git_multi_pack_index_write_config(const char *var, const char *value,
 	return 0;
 }
 
+static void read_packs_from_stdin(struct string_list *to)
+{
+	struct strbuf buf = STRBUF_INIT;
+	while (strbuf_getline(&buf, stdin) != EOF)
+		string_list_append(to, buf.buf);
+	string_list_sort(to);
+
+	strbuf_release(&buf);
+}
+
 static int cmd_multi_pack_index_write(int argc, const char **argv)
 {
 	struct option *options;
@@ -88,6 +101,10 @@ static int cmd_multi_pack_index_write(int argc, const char **argv)
 			MIDX_WRITE_BITMAP | MIDX_WRITE_REV_INDEX),
 		OPT_BIT(0, "progress", &opts.flags,
 			N_("force progress reporting"), MIDX_PROGRESS),
+		OPT_BOOL(0, "stdin-packs", &opts.stdin_packs,
+			 N_("write multi-pack index containing only given indexes")),
+		OPT_FILENAME(0, "refs-snapshot", &opts.refs_snapshot,
+			     N_("refs snapshot for selecting bitmap commits")),
 		OPT_END(),
 	};
 
@@ -110,8 +127,23 @@ static int cmd_multi_pack_index_write(int argc, const char **argv)
 
 	FREE_AND_NULL(options);
 
+	if (opts.stdin_packs) {
+		struct string_list packs = STRING_LIST_INIT_DUP;
+		int ret;
+
+		read_packs_from_stdin(&packs);
+
+		ret = write_midx_file_only(opts.object_dir, &packs,
+					   opts.preferred_pack,
+					   opts.refs_snapshot, opts.flags);
+
+		string_list_clear(&packs, 0);
+
+		return ret;
+
+	}
 	return write_midx_file(opts.object_dir, opts.preferred_pack,
-			       opts.flags);
+			       opts.refs_snapshot, opts.flags);
 }
 
 static int cmd_multi_pack_index_verify(int argc, const char **argv)

builtin/repack.c

@@ -15,6 +15,8 @@
 #include "promisor-remote.h"
 #include "shallow.h"
 #include "pack.h"
+#include "pack-bitmap.h"
+#include "refs.h"
 
 static int delta_base_offset = 1;
 static int pack_kept_objects = -1;
@@ -94,12 +96,14 @@ static void remove_pack_on_signal(int signo)
 }
 
 /*
- * Adds all packs hex strings to the fname list, which do not
- * have a corresponding .keep file. These packs are not to
- * be kept if we are going to pack everything into one file.
+ * Adds all packs hex strings to either fname_nonkept_list or
+ * fname_kept_list based on whether each pack has a corresponding
+ * .keep file or not.  Packs without a .keep file are not to be kept
+ * if we are going to pack everything into one file.
  */
-static void get_non_kept_pack_filenames(struct string_list *fname_list,
-					const struct string_list *extra_keep)
+static void collect_pack_filenames(struct string_list *fname_nonkept_list,
+				   struct string_list *fname_kept_list,
+				   const struct string_list *extra_keep)
 {
 	DIR *dir;
 	struct dirent *e;
@@ -112,21 +116,20 @@ static void get_non_kept_pack_filenames(struct string_list *fname_list,
 		size_t len;
 		int i;
 
+		if (!strip_suffix(e->d_name, ".pack", &len))
+			continue;
+
 		for (i = 0; i < extra_keep->nr; i++)
 			if (!fspathcmp(e->d_name, extra_keep->items[i].string))
 				break;
-		if (extra_keep->nr > 0 && i < extra_keep->nr)
-			continue;
-
-		if (!strip_suffix(e->d_name, ".pack", &len))
-			continue;
 
 		fname = xmemdupz(e->d_name, len);
 
-		if (!file_exists(mkpath("%s/%s.keep", packdir, fname)))
-			string_list_append_nodup(fname_list, fname);
+		if ((extra_keep->nr > 0 && i < extra_keep->nr) ||
+		    (file_exists(mkpath("%s/%s.keep", packdir, fname))))
+			string_list_append_nodup(fname_kept_list, fname);
 		else
-			free(fname);
+			string_list_append_nodup(fname_nonkept_list, fname);
 	}
 	closedir(dir);
 }
@@ -422,6 +425,25 @@ static void split_pack_geometry(struct pack_geometry *geometry, int factor)
 	geometry->split = split;
 }
 
+static struct packed_git *get_largest_active_pack(struct pack_geometry *geometry)
+{
+	if (!geometry) {
+		/*
+		 * No geometry means either an all-into-one repack (in which
+		 * case there is only one pack left and it is the largest) or an
+		 * incremental one.
+		 *
+		 * If repacking incrementally, then we could check the size of
+		 * all packs to determine which should be preferred, but leave
+		 * this for later.
+		 */
+		return NULL;
+	}
+	if (geometry->split == geometry->pack_nr)
+		return NULL;
+	return geometry->pack[geometry->pack_nr - 1];
+}
+
 static void clear_pack_geometry(struct pack_geometry *geometry)
 {
 	if (!geometry)
@@ -433,17 +455,162 @@ static void clear_pack_geometry(struct pack_geometry *geometry)
 	geometry->split = 0;
 }
 
+struct midx_snapshot_ref_data {
+	struct tempfile *f;
+	struct oidset seen;
+	int preferred;
+};
+
+static int midx_snapshot_ref_one(const char *refname,
+				 const struct object_id *oid,
+				 int flag, void *_data)
+{
+	struct midx_snapshot_ref_data *data = _data;
+	struct object_id peeled;
+
+	if (!peel_iterated_oid(oid, &peeled))
+		oid = &peeled;
+
+	if (oidset_insert(&data->seen, oid))
+		return 0; /* already seen */
+
+	if (oid_object_info(the_repository, oid, NULL) != OBJ_COMMIT)
+		return 0;
+
+	fprintf(data->f->fp, "%s%s\n", data->preferred ? "+" : "",
+		oid_to_hex(oid));
+
+	return 0;
+}
+
+static void midx_snapshot_refs(struct tempfile *f)
+{
+	struct midx_snapshot_ref_data data;
+	const struct string_list *preferred = bitmap_preferred_tips(the_repository);
+
+	data.f = f;
+	data.preferred = 0;
+	oidset_init(&data.seen, 0);
+
+	if (!fdopen_tempfile(f, "w"))
+		 die(_("could not open tempfile %s for writing"),
+		     get_tempfile_path(f));
+
+	if (preferred) {
+		struct string_list_item *item;
+
+		data.preferred = 1;
+		for_each_string_list_item(item, preferred)
+			for_each_ref_in(item->string, midx_snapshot_ref_one, &data);
+		data.preferred = 0;
+	}
+
+	for_each_ref(midx_snapshot_ref_one, &data);
+
+	if (close_tempfile_gently(f)) {
+		int save_errno = errno;
+		delete_tempfile(&f);
+		errno = save_errno;
+		die_errno(_("could not close refs snapshot tempfile"));
+	}
+
+	oidset_clear(&data.seen);
+}
+
+static void midx_included_packs(struct string_list *include,
+				struct string_list *existing_nonkept_packs,
+				struct string_list *existing_kept_packs,
+				struct string_list *names,
+				struct pack_geometry *geometry)
+{
+	struct string_list_item *item;
+
+	for_each_string_list_item(item, existing_kept_packs)
+		string_list_insert(include, xstrfmt("%s.idx", item->string));
+	for_each_string_list_item(item, names)
+		string_list_insert(include, xstrfmt("pack-%s.idx", item->string));
+	if (geometry) {
+		struct strbuf buf = STRBUF_INIT;
+		uint32_t i;
+		for (i = geometry->split; i < geometry->pack_nr; i++) {
+			struct packed_git *p = geometry->pack[i];
+
+			strbuf_addstr(&buf, pack_basename(p));
+			strbuf_strip_suffix(&buf, ".pack");
+			strbuf_addstr(&buf, ".idx");
+
+			string_list_insert(include, strbuf_detach(&buf, NULL));
+		}
+	} else {
+		for_each_string_list_item(item, existing_nonkept_packs) {
+			if (item->util)
+				continue;
+			string_list_insert(include, xstrfmt("%s.idx", item->string));
+		}
+	}
+}
+
+static int write_midx_included_packs(struct string_list *include,
+				     struct pack_geometry *geometry,
+				     const char *refs_snapshot,
+				     int show_progress, int write_bitmaps)
+{
+	struct child_process cmd = CHILD_PROCESS_INIT;
+	struct string_list_item *item;
+	struct packed_git *largest = get_largest_active_pack(geometry);
+	FILE *in;
+	int ret;
+
+	if (!include->nr)
+		return 0;
+
+	cmd.in = -1;
+	cmd.git_cmd = 1;
+
+	strvec_push(&cmd.args, "multi-pack-index");
+	strvec_pushl(&cmd.args, "write", "--stdin-packs", NULL);
+
+	if (show_progress)
+		strvec_push(&cmd.args, "--progress");
+	else
+		strvec_push(&cmd.args, "--no-progress");
+
+	if (write_bitmaps)
+		strvec_push(&cmd.args, "--bitmap");
+
+	if (largest)
+		strvec_pushf(&cmd.args, "--preferred-pack=%s",
+			     pack_basename(largest));
+
+	if (refs_snapshot)
+		strvec_pushf(&cmd.args, "--refs-snapshot=%s", refs_snapshot);
+
+	ret = start_command(&cmd);
+	if (ret)
+		return ret;
+
+	in = xfdopen(cmd.in, "w");
+	for_each_string_list_item(item, include)
+		fprintf(in, "%s\n", item->string);
+	fclose(in);
+
+	return finish_command(&cmd);
+}
+
 int cmd_repack(int argc, const char **argv, const char *prefix)
 {
 	struct child_process cmd = CHILD_PROCESS_INIT;
 	struct string_list_item *item;
 	struct string_list names = STRING_LIST_INIT_DUP;
 	struct string_list rollback = STRING_LIST_INIT_NODUP;
-	struct string_list existing_packs = STRING_LIST_INIT_DUP;
+	struct string_list existing_nonkept_packs = STRING_LIST_INIT_DUP;
+	struct string_list existing_kept_packs = STRING_LIST_INIT_DUP;
 	struct pack_geometry *geometry = NULL;
 	struct strbuf line = STRBUF_INIT;
+	struct tempfile *refs_snapshot = NULL;
 	int i, ext, ret;
 	FILE *out;
+	int show_progress = isatty(2);
 
 	/* variables to be filled by option parsing */
 	int pack_everything = 0;
@@ -454,6 +621,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	int no_update_server_info = 0;
 	struct pack_objects_args po_args = {NULL};
 	int geometric_factor = 0;
+	int write_midx = 0;
 
 	struct option builtin_repack_options[] = {
 		OPT_BIT('a', NULL, &pack_everything,
@@ -496,6 +664,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 				N_("do not repack this pack")),
 		OPT_INTEGER('g', "geometric", &geometric_factor,
 			    N_("find a geometric progression with factor <N>")),
+		OPT_BOOL('m', "write-midx", &write_midx,
+			   N_("write a multi-pack index of the resulting packs")),
 		OPT_END()
 	};
 
@@ -512,8 +682,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		die(_("--keep-unreachable and -A are incompatible"));
 
 	if (write_bitmaps < 0) {
-		if (!(pack_everything & ALL_INTO_ONE) ||
-		    !is_bare_repository())
+		if (!write_midx &&
+		    (!(pack_everything & ALL_INTO_ONE) || !is_bare_repository()))
 			write_bitmaps = 0;
 	} else if (write_bitmaps &&
 		   git_env_bool(GIT_TEST_MULTI_PACK_INDEX, 0) &&
@@ -523,9 +693,21 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	if (pack_kept_objects < 0)
 		pack_kept_objects = write_bitmaps > 0;
 
-	if (write_bitmaps && !(pack_everything & ALL_INTO_ONE))
+	if (write_bitmaps && !(pack_everything & ALL_INTO_ONE) && !write_midx)
 		die(_(incremental_bitmap_conflict_error));
 
+	if (write_midx && write_bitmaps) {
+		struct strbuf path = STRBUF_INIT;
+
+		strbuf_addf(&path, "%s/%s_XXXXXX", get_object_directory(),
+			    "bitmap-ref-tips");
+
+		refs_snapshot = xmks_tempfile(path.buf);
+		midx_snapshot_refs(refs_snapshot);
+
+		strbuf_release(&path);
+	}
+
 	if (geometric_factor) {
 		if (pack_everything)
 			die(_("--geometric is incompatible with -A, -a"));
@@ -565,19 +747,22 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	}
 	if (has_promisor_remote())
 		strvec_push(&cmd.args, "--exclude-promisor-objects");
-	if (write_bitmaps > 0)
-		strvec_push(&cmd.args, "--write-bitmap-index");
-	else if (write_bitmaps < 0)
-		strvec_push(&cmd.args, "--write-bitmap-index-quiet");
+	if (!write_midx) {
+		if (write_bitmaps > 0)
+			strvec_push(&cmd.args, "--write-bitmap-index");
+		else if (write_bitmaps < 0)
+			strvec_push(&cmd.args, "--write-bitmap-index-quiet");
+	}
 	if (use_delta_islands)
 		strvec_push(&cmd.args, "--delta-islands");
 
-	if (pack_everything & ALL_INTO_ONE) {
-		get_non_kept_pack_filenames(&existing_packs, &keep_pack_list);
+	collect_pack_filenames(&existing_nonkept_packs, &existing_kept_packs,
+			       &keep_pack_list);
 
+	if (pack_everything & ALL_INTO_ONE) {
 		repack_promisor_objects(&po_args, &names);
 
-		if (existing_packs.nr && delete_redundant) {
+		if (existing_nonkept_packs.nr && delete_redundant) {
 			for_each_string_list_item(item, &names) {
 				strvec_pushf(&cmd.args, "--keep-pack=%s-%s.pack",
 					     packtmp_name, item->string);
@@ -677,20 +862,48 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	}
 	/* End of pack replacement. */
 
-	reprepare_packed_git(the_repository);
-
-	if (delete_redundant) {
+	if (delete_redundant && pack_everything & ALL_INTO_ONE) {
 		const int hexsz = the_hash_algo->hexsz;
-		int opts = 0;
 		string_list_sort(&names);
-		for_each_string_list_item(item, &existing_packs) {
+		for_each_string_list_item(item, &existing_nonkept_packs) {
 			char *sha1;
 			size_t len = strlen(item->string);
 			if (len < hexsz)
 				continue;
 			sha1 = item->string + len - hexsz;
-			if (!string_list_has_string(&names, sha1))
-				remove_redundant_pack(packdir, item->string);
+			/*
+			 * Mark this pack for deletion, which ensures that this
+			 * pack won't be included in a MIDX (if `--write-midx`
+			 * was given) and that we will actually delete this pack
+			 * (if `-d` was given).
+			 */
+			item->util = (void*)(intptr_t)!string_list_has_string(&names, sha1);
+		}
+	}
+
+	if (write_midx) {
+		struct string_list include = STRING_LIST_INIT_NODUP;
+		midx_included_packs(&include, &existing_nonkept_packs,
+				    &existing_kept_packs, &names, geometry);
+
+		ret = write_midx_included_packs(&include, geometry,
+						refs_snapshot ? get_tempfile_path(refs_snapshot) : NULL,
+						show_progress, write_bitmaps > 0);
+
+		string_list_clear(&include, 0);
+
+		if (ret)
+			return ret;
+	}
+
+	reprepare_packed_git(the_repository);
+
+	if (delete_redundant) {
+		int opts = 0;
+		for_each_string_list_item(item, &existing_nonkept_packs) {
+			if (!item->util)
+				continue;
+			remove_redundant_pack(packdir, item->string);
 		}
 
 		if (geometry) {
@@ -711,7 +924,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 			}
 			strbuf_release(&buf);
 		}
-		if (!po_args.quiet && isatty(2))
+		if (!po_args.quiet && show_progress)
 			opts |= PRUNE_PACKED_VERBOSE;
 		prune_packed_objects(opts);
 
@@ -730,12 +943,13 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		unsigned flags = 0;
 		if (git_env_bool(GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP, 0))
 			flags |= MIDX_WRITE_BITMAP | MIDX_WRITE_REV_INDEX;
-		write_midx_file(get_object_directory(), NULL, flags);
+		write_midx_file(get_object_directory(), NULL, NULL, flags);
 	}
 
 	string_list_clear(&names, 0);
 	string_list_clear(&rollback, 0);
-	string_list_clear(&existing_packs, 0);
+	string_list_clear(&existing_nonkept_packs, 0);
+	string_list_clear(&existing_kept_packs, 0);
 	clear_pack_geometry(geometry);
 	strbuf_release(&line);
 

midx.c

@@ -460,6 +460,8 @@ 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 +471,26 @@ 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 +968,43 @@ 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 +1013,12 @@ 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 +1047,7 @@ 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 +1063,7 @@ 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
@@ -1047,8 +1108,10 @@ cleanup:
 }
 
 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;
@@ -1071,10 +1134,17 @@ static int write_midx_internal(const char *object_dir,
 		die_errno(_("unable to create leading directories of %s"),
 			  midx_name);
 
-	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.
+		 */
+		for (cur = get_multi_pack_index(the_repository); cur; cur = cur->next) {
+			if (!strcmp(object_dir, cur->object_dir)) {
+				ctx.m = cur;
+				break;
+			}
 		}
 	}
 
@@ -1125,10 +1195,13 @@ 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;
@@ -1332,7 +1405,8 @@ static int write_midx_internal(const char *object_dir,
 	if (flags & MIDX_WRITE_REV_INDEX)
 		write_midx_reverse_index(midx_name, 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, midx_hash, &ctx,
+				      refs_snapshot, flags) < 0) {
 			error(_("could not write multi-pack bitmap"));
 			result = 1;
 			goto cleanup;
@@ -1367,9 +1441,21 @@ cleanup:
 
 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 {
@@ -1649,7 +1735,7 @@ 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);
+		result = write_midx_internal(object_dir, NULL, &packs_to_drop, NULL, NULL, flags);
 		m = NULL;
 	}
 
@@ -1840,7 +1926,7 @@ 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);
+	result = write_midx_internal(object_dir, NULL, NULL, NULL, NULL, flags);
 	m = NULL;
 
 cleanup:

midx.h

@@ -2,6 +2,7 @@
 #define MIDX_H
 
 #include "repository.h"
+#include "string-list.h"
 
 struct object_id;
 struct pack_entry;
@@ -62,7 +63,19 @@ int fill_midx_entry(struct repository *r, const struct object_id *oid, struct pa
 int midx_contains_pack(struct multi_pack_index *m, const char *idx_or_pack_name);
 int prepare_multi_pack_index_one(struct repository *r, const char *object_dir, int local);
 
-int write_midx_file(const char *object_dir, const char *preferred_pack_name, unsigned flags);
+/*
+ * Variant of write_midx_file which writes a MIDX containing only the packs
+ * specified in packs_to_include.
+ */
+int write_midx_file(const char *object_dir,
+		    const char *preferred_pack_name,
+		    const char *refs_snapshot,
+		    unsigned 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);
 void clear_midx_file(struct repository *r);
 int verify_midx_file(struct repository *r, const char *object_dir, unsigned flags);
 int expire_midx_packs(struct repository *r, const char *object_dir, unsigned flags);

pack-bitmap.c

@@ -1418,7 +1418,7 @@ static int try_partial_reuse(struct packed_git *pack,
 	return 0;
 }
 
-static uint32_t midx_preferred_pack(struct bitmap_index *bitmap_git)
+uint32_t midx_preferred_pack(struct bitmap_index *bitmap_git)
 {
 	struct multi_pack_index *m = bitmap_git->midx;
 	if (!m)

pack-bitmap.h

@@ -56,6 +56,7 @@ int test_bitmap_hashes(struct repository *r);
 struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs,
 					 struct list_objects_filter_options *filter,
 					 int filter_provided_objects);
+uint32_t midx_preferred_pack(struct bitmap_index *bitmap_git);
 int reuse_partial_packfile_from_bitmap(struct bitmap_index *,
 				       struct packed_git **packfile,
 				       uint32_t *entries,

t/helper/test-read-midx.c

@@ -3,6 +3,7 @@
 #include "midx.h"
 #include "repository.h"
 #include "object-store.h"
+#include "pack-bitmap.h"
 
 static int read_midx_file(const char *object_dir, int show_objects)
 {
@@ -72,14 +73,40 @@ static int read_midx_checksum(const char *object_dir)
 	return 0;
 }
 
+static int read_midx_preferred_pack(const char *object_dir)
+{
+	struct multi_pack_index *midx = NULL;
+	struct bitmap_index *bitmap = NULL;
+
+	setup_git_directory();
+
+	midx = load_multi_pack_index(object_dir, 1);
+	if (!midx)
+		return 1;
+
+	bitmap = prepare_bitmap_git(the_repository);
+	if (!bitmap)
+		return 1;
+	if (!bitmap_is_midx(bitmap)) {
+		free_bitmap_index(bitmap);
+		return 1;
+	}
+
+	printf("%s\n", midx->pack_names[midx_preferred_pack(bitmap)]);
+	free_bitmap_index(bitmap);
+	return 0;
+}
+
 int cmd__read_midx(int argc, const char **argv)
 {
 	if (!(argc == 2 || argc == 3))
-		usage("read-midx [--show-objects|--checksum] <object-dir>");
+		usage("read-midx [--show-objects|--checksum|--preferred-pack] <object-dir>");
 
 	if (!strcmp(argv[1], "--show-objects"))
 		return read_midx_file(argv[2], 1);
 	else if (!strcmp(argv[1], "--checksum"))
 		return read_midx_checksum(argv[2]);
+	else if (!strcmp(argv[1], "--preferred-pack"))
+		return read_midx_preferred_pack(argv[2]);
 	return read_midx_file(argv[1], 0);
 }

t/lib-midx.sh

@@ -0,0 +1,8 @@
+# test_midx_consistent <objdir>
+test_midx_consistent () {
+	ls $1/pack/pack-*.idx | xargs -n 1 basename | sort >expect &&
+	test-tool read-midx $1 | grep ^pack-.*\.idx$ | sort >actual &&
+
+	test_cmp expect actual &&
+	git multi-pack-index --object-dir=$1 verify
+}

t/t5319-multi-pack-index.sh

@@ -168,6 +168,21 @@ test_expect_success 'write midx with two packs' '
 
 compare_results_with_midx "two packs"
 
+test_expect_success 'write midx with --stdin-packs' '
+	rm -fr $objdir/pack/multi-pack-index &&
+
+	idx="$(find $objdir/pack -name "test-2-*.idx")" &&
+	basename "$idx" >in &&
+
+	git multi-pack-index write --stdin-packs <in &&
+
+	test-tool read-midx $objdir | grep "\.idx$" >packs &&
+
+	test_cmp packs in
+'
+
+compare_results_with_midx "mixed mode (one pack + extra)"
+
 test_expect_success 'write progress off for redirected stderr' '
 	git multi-pack-index --object-dir=$objdir write 2>err &&
 	test_line_count = 0 err

t/t5326-multi-pack-bitmaps.sh

@@ -283,6 +283,88 @@ test_expect_success 'pack.preferBitmapTips' '
 	)
 '
 
+test_expect_success 'writing a bitmap with --refs-snapshot' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit one &&
+		test_commit two &&
+
+		git rev-parse one >snapshot &&
+
+		git repack -ad &&
+
+		# First, write a MIDX which see both refs/tags/one and
+		# refs/tags/two (causing both of those commits to receive
+		# bitmaps).
+		git multi-pack-index write --bitmap &&
+
+		test_path_is_file $midx &&
+		test_path_is_file $midx-$(midx_checksum $objdir).bitmap &&
+
+		test-tool bitmap list-commits | sort >bitmaps &&
+		grep "$(git rev-parse one)" bitmaps &&
+		grep "$(git rev-parse two)" bitmaps &&
+
+		rm -fr $midx-$(midx_checksum $objdir).bitmap &&
+		rm -fr $midx-$(midx_checksum $objdir).rev &&
+		rm -fr $midx &&
+
+		# Then again, but with a refs snapshot which only sees
+		# refs/tags/one.
+		git multi-pack-index write --bitmap --refs-snapshot=snapshot &&
+
+		test_path_is_file $midx &&
+		test_path_is_file $midx-$(midx_checksum $objdir).bitmap &&
+
+		test-tool bitmap list-commits | sort >bitmaps &&
+		grep "$(git rev-parse one)" bitmaps &&
+		! grep "$(git rev-parse two)" bitmaps
+	)
+'
+
+test_expect_success 'write a bitmap with --refs-snapshot (preferred tips)' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit_bulk --message="%s" 103 &&
+
+		git log --format="%H" >commits.raw &&
+		sort <commits.raw >commits &&
+
+		git log --format="create refs/tags/%s %H" HEAD >refs &&
+		git update-ref --stdin <refs &&
+
+		git multi-pack-index write --bitmap &&
+		test_path_is_file $midx &&
+		test_path_is_file $midx-$(midx_checksum $objdir).bitmap &&
+
+		test-tool bitmap list-commits | sort >bitmaps &&
+		comm -13 bitmaps commits >before &&
+		test_line_count = 1 before &&
+
+		(
+			grep -vf before commits.raw &&
+			# mark missing commits as preferred
+			sed "s/^/+/" before
+		) >snapshot &&
+
+		rm -fr $midx-$(midx_checksum $objdir).bitmap &&
+		rm -fr $midx-$(midx_checksum $objdir).rev &&
+		rm -fr $midx &&
+
+		git multi-pack-index write --bitmap --refs-snapshot=snapshot &&
+		test-tool bitmap list-commits | sort >bitmaps &&
+		comm -13 bitmaps commits >after &&
+
+		! test_cmp before after
+	)
+'
+
 test_expect_success 'hash-cache values are propagated from pack bitmaps' '
 	rm -fr repo &&
 	git init repo &&

t/t7700-repack.sh

@@ -3,6 +3,8 @@
 test_description='git repack works correctly'
 
 . ./test-lib.sh
+. "${TEST_DIRECTORY}/lib-bitmap.sh"
+. "${TEST_DIRECTORY}/lib-midx.sh"
 
 commit_and_pack () {
 	test_commit "$@" 1>&2 &&
@@ -234,4 +236,140 @@ test_expect_success 'auto-bitmaps do not complain if unavailable' '
 	test_must_be_empty actual
 '
 
+objdir=.git/objects
+midx=$objdir/pack/multi-pack-index
+
+test_expect_success 'setup for --write-midx tests' '
+	git init midx &&
+	(
+		cd midx &&
+		git config core.multiPackIndex true &&
+
+		test_commit base
+	)
+'
+
+test_expect_success '--write-midx unchanged' '
+	(
+		cd midx &&
+		GIT_TEST_MULTI_PACK_INDEX=0 git repack &&
+		test_path_is_missing $midx &&
+		test_path_is_missing $midx-*.bitmap &&
+
+		GIT_TEST_MULTI_PACK_INDEX=0 git repack --write-midx &&
+
+		test_path_is_file $midx &&
+		test_path_is_missing $midx-*.bitmap &&
+		test_midx_consistent $objdir
+	)
+'
+
+test_expect_success '--write-midx with a new pack' '
+	(
+		cd midx &&
+		test_commit loose &&
+
+		GIT_TEST_MULTI_PACK_INDEX=0 git repack --write-midx &&
+
+		test_path_is_file $midx &&
+		test_path_is_missing $midx-*.bitmap &&
+		test_midx_consistent $objdir
+	)
+'
+
+test_expect_success '--write-midx with -b' '
+	(
+		cd midx &&
+		GIT_TEST_MULTI_PACK_INDEX=0 git repack -mb &&
+
+		test_path_is_file $midx &&
+		test_path_is_file $midx-*.bitmap &&
+		test_midx_consistent $objdir
+	)
+'
+
+test_expect_success '--write-midx with -d' '
+	(
+		cd midx &&
+		test_commit repack &&
+
+		GIT_TEST_MULTI_PACK_INDEX=0 git repack -Ad --write-midx &&
+
+		test_path_is_file $midx &&
+		test_path_is_missing $midx-*.bitmap &&
+		test_midx_consistent $objdir
+	)
+'
+
+test_expect_success 'cleans up MIDX when appropriate' '
+	(
+		cd midx &&
+
+		test_commit repack-2 &&
+		GIT_TEST_MULTI_PACK_INDEX=0 git repack -Adb --write-midx &&
+
+		checksum=$(midx_checksum $objdir) &&
+		test_path_is_file $midx &&
+		test_path_is_file $midx-$checksum.bitmap &&
+		test_path_is_file $midx-$checksum.rev &&
+
+		test_commit repack-3 &&
+		GIT_TEST_MULTI_PACK_INDEX=0 git repack -Adb --write-midx &&
+
+		test_path_is_file $midx &&
+		test_path_is_missing $midx-$checksum.bitmap &&
+		test_path_is_missing $midx-$checksum.rev &&
+		test_path_is_file $midx-$(midx_checksum $objdir).bitmap &&
+		test_path_is_file $midx-$(midx_checksum $objdir).rev &&
+
+		test_commit repack-4 &&
+		GIT_TEST_MULTI_PACK_INDEX=0 git repack -Adb &&
+
+		find $objdir/pack -type f -name "multi-pack-index*" >files &&
+		test_must_be_empty files
+	)
+'
+
+test_expect_success '--write-midx with preferred bitmap tips' '
+	git init midx-preferred-tips &&
+	test_when_finished "rm -fr midx-preferred-tips" &&
+	(
+		cd midx-preferred-tips &&
+
+		test_commit_bulk --message="%s" 103 &&
+
+		git log --format="%H" >commits.raw &&
+		sort <commits.raw >commits &&
+
+		git log --format="create refs/tags/%s/%s %H" HEAD >refs &&
+		git update-ref --stdin <refs &&
+
+		git repack --write-midx --write-bitmap-index &&
+		test_path_is_file $midx &&
+		test_path_is_file $midx-$(midx_checksum $objdir).bitmap &&
+
+		test-tool bitmap list-commits | sort >bitmaps &&
+		comm -13 bitmaps commits >before &&
+		test_line_count = 1 before &&
+
+		rm -fr $midx-$(midx_checksum $objdir).bitmap &&
+		rm -fr $midx-$(midx_checksum $objdir).rev &&
+		rm -fr $midx &&
+
+		# instead of constructing the snapshot ourselves (c.f., the test
+		# "write a bitmap with --refs-snapshot (preferred tips)" in
+		# t5326), mark the missing commit as preferred by adding it to
+		# the pack.preferBitmapTips configuration.
+		git for-each-ref --format="%(refname:rstrip=1)" \
+			--points-at="$(cat before)" >missing &&
+		git config pack.preferBitmapTips "$(cat missing)" &&
+		git repack --write-midx --write-bitmap-index &&
+
+		test-tool bitmap list-commits | sort >bitmaps &&
+		comm -13 bitmaps commits >after &&
+
+		! test_cmp before after
+	)
+'
+
 test_done

t/t7703-repack-geometric.sh

@@ -15,7 +15,7 @@ test_expect_success '--geometric with no packs' '
 	(
 		cd geometric &&
 
-		git repack --geometric 2 >out &&
+		git repack --write-midx --geometric 2 >out &&
 		test_i18ngrep "Nothing new to pack" out
 	)
 '
@@ -180,4 +180,26 @@ test_expect_success '--geometric ignores kept packs' '
 	)
 '
 
+test_expect_success '--geometric chooses largest MIDX preferred pack' '
+	git init geometric &&
+	test_when_finished "rm -fr geometric" &&
+	(
+		cd geometric &&
+
+		# These packs already form a geometric progression.
+		test_commit_bulk --start=1 1 && # 3 objects
+		test_commit_bulk --start=2 2 && # 6 objects
+		ls $objdir/pack/pack-*.idx >before &&
+		test_commit_bulk --start=4 4 && # 12 objects
+		ls $objdir/pack/pack-*.idx >after &&
+
+		git repack --geometric 2 -dbm &&
+
+		comm -3 before after | xargs -n 1 basename >expect &&
+		test-tool read-midx --preferred-pack $objdir >actual &&
+
+		test_cmp expect actual
+	)
+'
+
 test_done