1 files changed, 165 insertions, 81 deletions

diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index c6e2852d3c..58a9b16126 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -1,8 +1,10 @@
+#define USE_THE_REPOSITORY_VARIABLE
+#define DISABLE_SIGN_COMPARE_WARNINGS
+
 #include "builtin.h"
 #include "environment.h"
 #include "gettext.h"
 #include "hex.h"
-#include "repository.h"
 #include "config.h"
 #include "attr.h"
 #include "object.h"
@@ -239,6 +241,7 @@ static enum {
 static uint16_t write_bitmap_options = BITMAP_OPT_HASH_CACHE;
 
 static int exclude_promisor_objects;
+static int exclude_promisor_objects_best_effort;
 
 static int use_delta_islands;
 
@@ -266,6 +269,43 @@ struct configured_exclusion {
 static struct oidmap configured_exclusions;
 
 static struct oidset excluded_by_config;
+static int name_hash_version = -1;
+
+/**
+ * Check whether the name_hash_version chosen by user input is appropriate,
+ * and also validate whether it is compatible with other features.
+ */
+static void validate_name_hash_version(void)
+{
+	if (name_hash_version < 1 || name_hash_version > 2)
+		die(_("invalid --name-hash-version option: %d"), name_hash_version);
+	if (write_bitmap_index && name_hash_version != 1) {
+		warning(_("currently, --write-bitmap-index requires --name-hash-version=1"));
+		name_hash_version = 1;
+	}
+}
+
+static inline uint32_t pack_name_hash_fn(const char *name)
+{
+	static int seen_version = -1;
+
+	if (seen_version < 0)
+		seen_version = name_hash_version;
+	else if (seen_version != name_hash_version)
+		BUG("name hash version changed from %d to %d mid-process",
+		    seen_version, name_hash_version);
+
+	switch (name_hash_version) {
+	case 1:
+		return pack_name_hash(name);
+
+	case 2:
+		return pack_name_hash_v2((const unsigned char *)name);
+
+	default:
+		BUG("invalid name-hash version: %d", name_hash_version);
+	}
+}
 
 /*
  * stats
@@ -1100,78 +1140,64 @@ static void write_reused_pack_one(struct packed_git *reuse_packfile,
 
 static size_t write_reused_pack_verbatim(struct bitmapped_pack *reuse_packfile,
 					 struct hashfile *out,
-					 off_t pack_start,
 					 struct pack_window **w_curs)
 {
-	size_t pos = reuse_packfile->bitmap_pos;
+	size_t pos = 0;
 	size_t end;
 
-	if (pos % BITS_IN_EWORD) {
-		size_t word_pos = (pos / BITS_IN_EWORD);
-		size_t offset = pos % BITS_IN_EWORD;
-		size_t last;
-		eword_t word = reuse_packfile_bitmap->words[word_pos];
-
-		if (offset + reuse_packfile->bitmap_nr < BITS_IN_EWORD)
-			last = offset + reuse_packfile->bitmap_nr;
-		else
-			last = BITS_IN_EWORD;
-
-		for (; offset < last; offset++) {
-			if (word >> offset == 0)
-				return word_pos;
-			if (!bitmap_get(reuse_packfile_bitmap,
-					word_pos * BITS_IN_EWORD + offset))
-				return word_pos;
-		}
-
-		pos += BITS_IN_EWORD - (pos % BITS_IN_EWORD);
+	if (reuse_packfile->bitmap_pos) {
+		/*
+		 * We can't reuse whole chunks verbatim out of
+		 * non-preferred packs since we can't guarantee that
+		 * all duplicate objects were resolved in favor of
+		 * that pack.
+		 *
+		 * Even if we have a whole eword_t worth of bits that
+		 * could be reused, there may be objects between the
+		 * objects corresponding to the first and last bit of
+		 * that word which were selected from a different
+		 * pack, causing us to send duplicate or unwanted
+		 * objects.
+		 *
+		 * Handle non-preferred packs from within
+		 * write_reused_pack(), which inspects and reuses
+		 * individual bits.
+		 */
+		return reuse_packfile->bitmap_pos / BITS_IN_EWORD;
 	}
 
 	/*
-	 * Now we're going to copy as many whole eword_t's as possible.
-	 * "end" is the index of the last whole eword_t we copy, but
-	 * there may be additional bits to process. Those are handled
-	 * individually by write_reused_pack().
+	 * Only read through the last word whose bits all correspond
+	 * to objects in the given packfile, since we must stop at a
+	 * word boundary.
 	 *
-	 * Begin by advancing to the first word boundary in range of the
-	 * bit positions occupied by objects in "reuse_packfile". Then
-	 * pick the last word boundary in the same range. If we have at
-	 * least one word's worth of bits to process, continue on.
+	 * If there is no whole word to read (i.e. the packfile
+	 * contains fewer than BITS_IN_EWORD objects), then we'll
+	 * inspect bits one-by-one in write_reused_pack().
 	 */
-	end = reuse_packfile->bitmap_pos + reuse_packfile->bitmap_nr;
-	if (end % BITS_IN_EWORD)
-		end -= end % BITS_IN_EWORD;
-	if (pos >= end)
-		return reuse_packfile->bitmap_pos / BITS_IN_EWORD;
+	end = reuse_packfile->bitmap_nr / BITS_IN_EWORD;
+	if (reuse_packfile_bitmap->word_alloc < end)
+		BUG("fewer words than expected in reuse_packfile_bitmap");
 
-	while (pos < end &&
-	       reuse_packfile_bitmap->words[pos / BITS_IN_EWORD] == (eword_t)~0)
-		pos += BITS_IN_EWORD;
+	while (pos < end && reuse_packfile_bitmap->words[pos] == (eword_t)~0)
+		pos++;
 
-	if (pos > end)
-		pos = end;
+	if (pos) {
+		off_t to_write;
 
-	if (reuse_packfile->bitmap_pos < pos) {
-		off_t pack_start_off = pack_pos_to_offset(reuse_packfile->p, 0);
-		off_t pack_end_off = pack_pos_to_offset(reuse_packfile->p,
-							pos - reuse_packfile->bitmap_pos);
-
-		written += pos - reuse_packfile->bitmap_pos;
+		written = (pos * BITS_IN_EWORD);
+		to_write = pack_pos_to_offset(reuse_packfile->p, written)
+			- sizeof(struct pack_header);
 
 		/* We're recording one chunk, not one object. */
-		record_reused_object(pack_start_off,
-				     pack_start_off - (hashfile_total(out) - pack_start));
+		record_reused_object(sizeof(struct pack_header), 0);
 		hashflush(out);
 		copy_pack_data(out, reuse_packfile->p, w_curs,
-			pack_start_off, pack_end_off - pack_start_off);
+			sizeof(struct pack_header), to_write);
 
 		display_progress(progress_state, written);
 	}
-	if (pos % BITS_IN_EWORD)
-		BUG("attempted to jump past a word boundary to %"PRIuMAX,
-		    (uintmax_t)pos);
-	return pos / BITS_IN_EWORD;
+	return pos;
 }
 
 static void write_reused_pack(struct bitmapped_pack *reuse_packfile,
@@ -1183,8 +1209,7 @@ static void write_reused_pack(struct bitmapped_pack *reuse_packfile,
 	struct pack_window *w_curs = NULL;
 
 	if (allow_ofs_delta)
-		i = write_reused_pack_verbatim(reuse_packfile, f, pack_start,
-					       &w_curs);
+		i = write_reused_pack_verbatim(reuse_packfile, f, &w_curs);
 
 	for (; i < reuse_packfile_bitmap->word_alloc; ++i) {
 		eword_t word = reuse_packfile_bitmap->words[i];
@@ -1276,7 +1301,8 @@ static void write_pack_file(void)
 	struct object_entry **write_order;
 
 	if (progress > pack_to_stdout)
-		progress_state = start_progress(_("Writing objects"), nr_result);
+		progress_state = start_progress(the_repository,
+						_("Writing objects"), nr_result);
 	ALLOC_ARRAY(written_list, to_pack.nr_objects);
 	write_order = compute_write_order();
 
@@ -1330,8 +1356,9 @@ static void write_pack_file(void)
 			 */
 
 			int fd = finalize_hashfile(f, hash, FSYNC_COMPONENT_PACK, 0);
-			fixup_pack_header_footer(fd, hash, pack_tmp_name,
-						 nr_written, hash, offset);
+			fixup_pack_header_footer(the_hash_algo, fd, hash,
+						 pack_tmp_name, nr_written,
+						 hash, offset);
 			close(fd);
 			if (write_bitmap_index) {
 				if (write_bitmap_index != WRITE_BITMAP_QUIET)
@@ -1379,9 +1406,10 @@ static void write_pack_file(void)
 			if (cruft)
 				pack_idx_opts.flags |= WRITE_MTIMES;
 
-			stage_tmp_packfiles(&tmpname, pack_tmp_name,
-					    written_list, nr_written,
-					    &to_pack, &pack_idx_opts, hash,
+			stage_tmp_packfiles(the_hash_algo, &tmpname,
+					    pack_tmp_name, written_list,
+					    nr_written, &to_pack,
+					    &pack_idx_opts, hash,
 					    &idx_tmp_name);
 
 			if (write_bitmap_index) {
@@ -1529,7 +1557,7 @@ static int want_found_object(const struct object_id *oid, int exclude,
 			return 0;
 		if (ignore_packed_keep_in_core && p->pack_keep_in_core)
 			return 0;
-		if (has_object_kept_pack(oid, flags))
+		if (has_object_kept_pack(p->repo, oid, flags))
 			return 0;
 	}
 
@@ -1556,7 +1584,7 @@ static int want_object_in_pack_one(struct packed_git *p,
 	if (p == *found_pack)
 		offset = *found_offset;
 	else
-		offset = find_pack_entry_one(oid->hash, p);
+		offset = find_pack_entry_one(oid, p);
 
 	if (offset) {
 		if (!*found_pack) {
@@ -1698,7 +1726,7 @@ static int add_object_entry(const struct object_id *oid, enum object_type type,
 		return 0;
 	}
 
-	create_object_entry(oid, type, pack_name_hash(name),
+	create_object_entry(oid, type, pack_name_hash_fn(name),
 			    exclude, name && no_try_delta(name),
 			    found_pack, found_offset);
 	return 1;
@@ -1912,7 +1940,7 @@ static void add_preferred_base_object(const char *name)
 {
 	struct pbase_tree *it;
 	size_t cmplen;
-	unsigned hash = pack_name_hash(name);
+	unsigned hash = pack_name_hash_fn(name);
 
 	if (!num_preferred_base || check_pbase_path(hash))
 		return;
@@ -2412,7 +2440,8 @@ static void get_object_details(void)
 	struct object_entry **sorted_by_offset;
 
 	if (progress)
-		progress_state = start_progress(_("Counting objects"),
+		progress_state = start_progress(the_repository,
+						_("Counting objects"),
 						to_pack.nr_objects);
 
 	CALLOC_ARRAY(sorted_by_offset, to_pack.nr_objects);
@@ -3232,7 +3261,8 @@ static void prepare_pack(int window, int depth)
 		unsigned nr_done = 0;
 
 		if (progress)
-			progress_state = start_progress(_("Compressing objects"),
+			progress_state = start_progress(the_repository,
+							_("Compressing objects"),
 							nr_deltas);
 		QSORT(delta_list, n, type_size_sort);
 		ll_find_deltas(delta_list, n, window+1, depth, &nr_done);
@@ -3422,7 +3452,7 @@ static void show_object_pack_hint(struct object *object, const char *name,
 	 * here using a now in order to perhaps improve the delta selection
 	 * process.
 	 */
-	oe->hash = pack_name_hash(name);
+	oe->hash = pack_name_hash_fn(name);
 	oe->no_try_delta = name && no_try_delta(name);
 
 	stdin_packs_hints_nr++;
@@ -3572,7 +3602,7 @@ static void add_cruft_object_entry(const struct object_id *oid, enum object_type
 	entry = packlist_find(&to_pack, oid);
 	if (entry) {
 		if (name) {
-			entry->hash = pack_name_hash(name);
+			entry->hash = pack_name_hash_fn(name);
 			entry->no_try_delta = no_try_delta(name);
 		}
 	} else {
@@ -3595,7 +3625,7 @@ static void add_cruft_object_entry(const struct object_id *oid, enum object_type
 			return;
 		}
 
-		entry = create_object_entry(oid, type, pack_name_hash(name),
+		entry = create_object_entry(oid, type, pack_name_hash_fn(name),
 					    0, name && no_try_delta(name),
 					    pack, offset);
 	}
@@ -3627,7 +3657,7 @@ static void show_cruft_commit(struct commit *commit, void *data)
 
 static int cruft_include_check_obj(struct object *obj, void *data UNUSED)
 {
-	return !has_object_kept_pack(&obj->oid, IN_CORE_KEEP_PACKS);
+	return !has_object_kept_pack(to_pack.repo, &obj->oid, IN_CORE_KEEP_PACKS);
 }
 
 static int cruft_include_check(struct commit *commit, void *data)
@@ -3660,7 +3690,8 @@ static void add_objects_in_unpacked_packs(void);
 static void enumerate_cruft_objects(void)
 {
 	if (progress)
-		progress_state = start_progress(_("Enumerating cruft objects"), 0);
+		progress_state = start_progress(the_repository,
+						_("Enumerating cruft objects"), 0);
 
 	add_objects_in_unpacked_packs();
 	add_unreachable_loose_objects();
@@ -3686,7 +3717,8 @@ static void enumerate_and_traverse_cruft_objects(struct string_list *fresh_packs
 	revs.ignore_missing_links = 1;
 
 	if (progress)
-		progress_state = start_progress(_("Enumerating cruft objects"), 0);
+		progress_state = start_progress(the_repository,
+						_("Enumerating cruft objects"), 0);
 	ret = add_unseen_recent_objects_to_traversal(&revs, cruft_expiration,
 						     set_cruft_mtime, 1);
 	stop_progress(&progress_state);
@@ -3705,7 +3737,8 @@ static void enumerate_and_traverse_cruft_objects(struct string_list *fresh_packs
 	if (prepare_revision_walk(&revs))
 		die(_("revision walk setup failed"));
 	if (progress)
-		progress_state = start_progress(_("Traversing cruft objects"), 0);
+		progress_state = start_progress(the_repository,
+						_("Traversing cruft objects"), 0);
 	nr_seen = 0;
 	traverse_commit_list(&revs, show_cruft_commit, show_cruft_object, NULL);
 
@@ -3858,7 +3891,8 @@ static void show_object__ma_allow_promisor(struct object *obj, const char *name,
 	 * Quietly ignore EXPECTED missing objects.  This avoids problems with
 	 * staging them now and getting an odd error later.
 	 */
-	if (!has_object(the_repository, &obj->oid, 0) && is_promisor_object(&obj->oid))
+	if (!has_object(the_repository, &obj->oid, 0) &&
+	    is_promisor_object(to_pack.repo, &obj->oid))
 		return;
 
 	show_object(obj, name, data);
@@ -3927,7 +3961,9 @@ static int add_object_in_unpacked_pack(const struct object_id *oid,
 
 static void add_objects_in_unpacked_packs(void)
 {
-	if (for_each_packed_object(add_object_in_unpacked_pack, NULL,
+	if (for_each_packed_object(to_pack.repo,
+				   add_object_in_unpacked_pack,
+				   NULL,
 				   FOR_EACH_OBJECT_PACK_ORDER |
 				   FOR_EACH_OBJECT_LOCAL_ONLY |
 				   FOR_EACH_OBJECT_SKIP_IN_CORE_KEPT_PACKS |
@@ -3968,7 +4004,7 @@ static int add_loose_object(const struct object_id *oid, const char *path,
  */
 static void add_unreachable_loose_objects(void)
 {
-	for_each_loose_file_in_objdir(get_object_directory(),
+	for_each_loose_file_in_objdir(repo_get_object_directory(the_repository),
 				      add_loose_object,
 				      NULL, NULL, NULL);
 }
@@ -3984,7 +4020,7 @@ static int has_sha1_pack_kept_or_nonlocal(const struct object_id *oid)
 	while (p) {
 		if ((!p->pack_local || p->pack_keep ||
 				p->pack_keep_in_core) &&
-			find_pack_entry_one(oid->hash, p)) {
+			find_pack_entry_one(oid, p)) {
 			last_found = p;
 			return 1;
 		}
@@ -4069,6 +4105,15 @@ static int get_object_list_from_bitmap(struct rev_info *revs)
 	if (!(bitmap_git = prepare_bitmap_walk(revs, 0)))
 		return -1;
 
+	/*
+	 * For now, force the name-hash version to be 1 since that
+	 * is the version implied by the bitmap format. Later, the
+	 * format can include this version explicitly in its format,
+	 * allowing readers to know the version that was used during
+	 * the bitmap write.
+	 */
+	name_hash_version = 1;
+
 	if (pack_options_allow_reuse())
 		reuse_partial_packfile_from_bitmap(bitmap_git,
 						   &reuse_packfiles,
@@ -4312,7 +4357,22 @@ static int option_parse_cruft_expiration(const struct option *opt UNUSED,
 	return 0;
 }
 
-int cmd_pack_objects(int argc, const char **argv, const char *prefix)
+static int is_not_in_promisor_pack_obj(struct object *obj, void *data UNUSED)
+{
+	struct object_info info = OBJECT_INFO_INIT;
+	if (oid_object_info_extended(the_repository, &obj->oid, &info, 0))
+		BUG("should_include_obj should only be called on existing objects");
+	return info.whence != OI_PACKED || !info.u.packed.pack->pack_promisor;
+}
+
+static int is_not_in_promisor_pack(struct commit *commit, void *data) {
+	return is_not_in_promisor_pack_obj((struct object *) commit, data);
+}
+
+int cmd_pack_objects(int argc,
+		     const char **argv,
+		     const char *prefix,
+		     struct repository *repo UNUSED)
 {
 	int use_internal_rev_list = 0;
 	int shallow = 0;
@@ -4421,11 +4481,16 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		  option_parse_missing_action),
 		OPT_BOOL(0, "exclude-promisor-objects", &exclude_promisor_objects,
 			 N_("do not pack objects in promisor packfiles")),
+		OPT_BOOL(0, "exclude-promisor-objects-best-effort",
+			 &exclude_promisor_objects_best_effort,
+			 N_("implies --missing=allow-any")),
 		OPT_BOOL(0, "delta-islands", &use_delta_islands,
 			 N_("respect islands during delta compression")),
 		OPT_STRING_LIST(0, "uri-protocol", &uri_protocols,
 				N_("protocol"),
 				N_("exclude any configured uploadpack.blobpackfileuri with this protocol")),
+		OPT_INTEGER(0, "name-hash-version", &name_hash_version,
+			 N_("use the specified name-hash function to group similar objects")),
 		OPT_END(),
 	};
 
@@ -4501,10 +4566,18 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		strvec_push(&rp, "--unpacked");
 	}
 
+	if (exclude_promisor_objects && exclude_promisor_objects_best_effort)
+		die(_("options '%s' and '%s' cannot be used together"),
+		    "--exclude-promisor-objects", "--exclude-promisor-objects-best-effort");
 	if (exclude_promisor_objects) {
 		use_internal_rev_list = 1;
 		fetch_if_missing = 0;
 		strvec_push(&rp, "--exclude-promisor-objects");
+	} else if (exclude_promisor_objects_best_effort) {
+		use_internal_rev_list = 1;
+		fetch_if_missing = 0;
+		option_parse_missing_action(NULL, "allow-any", 0);
+		/* revs configured below */
 	}
 	if (unpack_unreachable || keep_unreachable || pack_loose_unreachable)
 		use_internal_rev_list = 1;
@@ -4573,6 +4646,11 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	if (pack_to_stdout || !rev_list_all)
 		write_bitmap_index = 0;
 
+	if (name_hash_version < 0)
+		name_hash_version = (int)git_env_ulong("GIT_TEST_NAME_HASH_VERSION", 1);
+
+	validate_name_hash_version();
+
 	if (use_delta_islands)
 		strvec_push(&rp, "--topo-order");
 
@@ -4608,7 +4686,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	prepare_packing_data(the_repository, &to_pack);
 
 	if (progress && !cruft)
-		progress_state = start_progress(_("Enumerating objects"), 0);
+		progress_state = start_progress(the_repository,
+						_("Enumerating objects"), 0);
 	if (stdin_packs) {
 		/* avoids adding objects in excluded packs */
 		ignore_packed_keep_in_core = 1;
@@ -4624,6 +4703,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 
 		repo_init_revisions(the_repository, &revs, NULL);
 		list_objects_filter_copy(&revs.filter, &filter_options);
+		if (exclude_promisor_objects_best_effort) {
+			revs.include_check = is_not_in_promisor_pack;
+			revs.include_check_obj = is_not_in_promisor_pack_obj;
+		}
 		get_object_list(&revs, rp.nr, rp.v);
 		release_revisions(&revs);
 	}
@@ -4669,6 +4752,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 cleanup:
 	clear_packing_data(&to_pack);
 	list_objects_filter_release(&filter_options);
+	string_list_clear(&keep_pack_list, 0);
 	strvec_clear(&rp);
 
 	return 0;