1 files changed, 287 insertions, 185 deletions

diff --git a/commit-graph.c b/commit-graph.c
index e3420ddcbf..e51c91dd5b 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1,7 +1,5 @@
-#include "cache.h"
-#include "config.h"
-#include "dir.h"
 #include "git-compat-util.h"
+#include "config.h"
 #include "lockfile.h"
 #include "pack.h"
 #include "packfile.h"
@@ -19,6 +17,8 @@
 #include "bloom.h"
 #include "commit-slab.h"
 #include "shallow.h"
+#include "json-writer.h"
+#include "trace2.h"
 
 void git_test_write_commit_graph_or_die(void)
 {
@@ -87,15 +87,69 @@ static int commit_pos_cmp(const void *va, const void *vb)
 	       commit_pos_at(&commit_pos, b);
 }
 
+define_commit_slab(commit_graph_data_slab, struct commit_graph_data);
+static struct commit_graph_data_slab commit_graph_data_slab =
+	COMMIT_SLAB_INIT(1, commit_graph_data_slab);
+
+uint32_t commit_graph_position(const struct commit *c)
+{
+	struct commit_graph_data *data =
+		commit_graph_data_slab_peek(&commit_graph_data_slab, c);
+
+	return data ? data->graph_pos : COMMIT_NOT_FROM_GRAPH;
+}
+
+uint32_t commit_graph_generation(const struct commit *c)
+{
+	struct commit_graph_data *data =
+		commit_graph_data_slab_peek(&commit_graph_data_slab, c);
+
+	if (!data)
+		return GENERATION_NUMBER_INFINITY;
+	else if (data->graph_pos == COMMIT_NOT_FROM_GRAPH)
+		return GENERATION_NUMBER_INFINITY;
+
+	return data->generation;
+}
+
+static struct commit_graph_data *commit_graph_data_at(const struct commit *c)
+{
+	unsigned int i, nth_slab;
+	struct commit_graph_data *data =
+		commit_graph_data_slab_peek(&commit_graph_data_slab, c);
+
+	if (data)
+		return data;
+
+	nth_slab = c->index / commit_graph_data_slab.slab_size;
+	data = commit_graph_data_slab_at(&commit_graph_data_slab, c);
+
+	/*
+	 * commit-slab initializes elements with zero, overwrite this with
+	 * COMMIT_NOT_FROM_GRAPH for graph_pos.
+	 *
+	 * We avoid initializing generation with checking if graph position
+	 * is not COMMIT_NOT_FROM_GRAPH.
+	 */
+	for (i = 0; i < commit_graph_data_slab.slab_size; i++) {
+		commit_graph_data_slab.slab[nth_slab][i].graph_pos =
+			COMMIT_NOT_FROM_GRAPH;
+	}
+
+	return data;
+}
+
 static int commit_gen_cmp(const void *va, const void *vb)
 {
 	const struct commit *a = *(const struct commit **)va;
 	const struct commit *b = *(const struct commit **)vb;
 
+	uint32_t generation_a = commit_graph_generation(a);
+	uint32_t generation_b = commit_graph_generation(b);
 	/* lower generation commits first */
-	if (a->generation < b->generation)
+	if (generation_a < generation_b)
 		return -1;
-	else if (a->generation > b->generation)
+	else if (generation_a > generation_b)
 		return 1;
 
 	/* use date as a heuristic when generations are equal */
@@ -149,7 +203,8 @@ static int commit_graph_compatible(struct repository *r)
 	}
 
 	prepare_commit_graft(r);
-	if (r->parsed_objects && r->parsed_objects->grafts_nr)
+	if (r->parsed_objects &&
+	    (r->parsed_objects->grafts_nr || r->parsed_objects->substituted_parent))
 		return 0;
 	if (is_repository_shallow(r))
 		return 0;
@@ -230,8 +285,7 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
 	const unsigned char *data, *chunk_lookup;
 	uint32_t i;
 	struct commit_graph *graph;
-	uint64_t last_chunk_offset;
-	uint32_t last_chunk_id;
+	uint64_t next_chunk_offset;
 	uint32_t graph_signature;
 	unsigned char graph_version, hash_version;
 
@@ -271,24 +325,26 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
 	graph->data = graph_map;
 	graph->data_len = graph_size;
 
-	last_chunk_id = 0;
-	last_chunk_offset = 8;
+	if (graph_size < GRAPH_HEADER_SIZE +
+			 (graph->num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH +
+			 GRAPH_FANOUT_SIZE + the_hash_algo->rawsz) {
+		error(_("commit-graph file is too small to hold %u chunks"),
+		      graph->num_chunks);
+		free(graph);
+		return NULL;
+	}
+
 	chunk_lookup = data + 8;
+	next_chunk_offset = get_be64(chunk_lookup + 4);
 	for (i = 0; i < graph->num_chunks; i++) {
 		uint32_t chunk_id;
-		uint64_t chunk_offset;
+		uint64_t chunk_offset = next_chunk_offset;
 		int chunk_repeated = 0;
 
-		if (data + graph_size - chunk_lookup <
-		    GRAPH_CHUNKLOOKUP_WIDTH) {
-			error(_("commit-graph chunk lookup table entry missing; file may be incomplete"));
-			goto free_and_return;
-		}
-
 		chunk_id = get_be32(chunk_lookup + 0);
-		chunk_offset = get_be64(chunk_lookup + 4);
 
 		chunk_lookup += GRAPH_CHUNKLOOKUP_WIDTH;
+		next_chunk_offset = get_be64(chunk_lookup + 4);
 
 		if (chunk_offset > graph_size - the_hash_algo->rawsz) {
 			error(_("commit-graph improper chunk offset %08x%08x"), (uint32_t)(chunk_offset >> 32),
@@ -307,8 +363,11 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
 		case GRAPH_CHUNKID_OIDLOOKUP:
 			if (graph->chunk_oid_lookup)
 				chunk_repeated = 1;
-			else
+			else {
 				graph->chunk_oid_lookup = data + chunk_offset;
+				graph->num_commits = (next_chunk_offset - chunk_offset)
+						     / graph->hash_len;
+			}
 			break;
 
 		case GRAPH_CHUNKID_DATA:
@@ -362,15 +421,6 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
 			error(_("commit-graph chunk id %08x appears multiple times"), chunk_id);
 			goto free_and_return;
 		}
-
-		if (last_chunk_id == GRAPH_CHUNKID_OIDLOOKUP)
-		{
-			graph->num_commits = (chunk_offset - last_chunk_offset)
-					     / graph->hash_len;
-		}
-
-		last_chunk_id = chunk_id;
-		last_chunk_offset = chunk_offset;
 	}
 
 	if (graph->chunk_bloom_indexes && graph->chunk_bloom_data) {
@@ -569,10 +619,6 @@ static int prepare_commit_graph(struct repository *r)
 		return !!r->objects->commit_graph;
 	r->objects->commit_graph_attempted = 1;
 
-	if (git_env_bool(GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD, 0))
-		die("dying as requested by the '%s' variable on commit-graph load!",
-		    GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD);
-
 	prepare_repo_settings(r);
 
 	if (!git_env_bool(GIT_TEST_COMMIT_GRAPH, 0) &&
@@ -670,13 +716,14 @@ static struct commit_list **insert_parent_or_die(struct repository *r,
 	c = lookup_commit(r, &oid);
 	if (!c)
 		die(_("could not find commit %s"), oid_to_hex(&oid));
-	c->graph_pos = pos;
+	commit_graph_data_at(c)->graph_pos = pos;
 	return &commit_list_insert(c, pptr)->next;
 }
 
 static void fill_commit_graph_info(struct commit *item, struct commit_graph *g, uint32_t pos)
 {
 	const unsigned char *commit_data;
+	struct commit_graph_data *graph_data;
 	uint32_t lex_index;
 
 	while (pos < g->num_commits_in_base)
@@ -684,8 +731,10 @@ static void fill_commit_graph_info(struct commit *item, struct commit_graph *g,
 
 	lex_index = pos - g->num_commits_in_base;
 	commit_data = g->chunk_commit_data + GRAPH_DATA_WIDTH * lex_index;
-	item->graph_pos = pos;
-	item->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
+
+	graph_data = commit_graph_data_at(item);
+	graph_data->graph_pos = pos;
+	graph_data->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
 }
 
 static inline void set_commit_tree(struct commit *c, struct tree *t)
@@ -701,6 +750,7 @@ static int fill_commit_in_graph(struct repository *r,
 	uint32_t *parent_data_ptr;
 	uint64_t date_low, date_high;
 	struct commit_list **pptr;
+	struct commit_graph_data *graph_data;
 	const unsigned char *commit_data;
 	uint32_t lex_index;
 
@@ -714,7 +764,8 @@ static int fill_commit_in_graph(struct repository *r,
 	 * Store the "full" position, but then use the
 	 * "local" position for the rest of the calculation.
 	 */
-	item->graph_pos = pos;
+	graph_data = commit_graph_data_at(item);
+	graph_data->graph_pos = pos;
 	lex_index = pos - g->num_commits_in_base;
 
 	commit_data = g->chunk_commit_data + (g->hash_len + 16) * lex_index;
@@ -727,7 +778,7 @@ static int fill_commit_in_graph(struct repository *r,
 	date_low = get_be32(commit_data + g->hash_len + 12);
 	item->date = (timestamp_t)((date_high << 32) | date_low);
 
-	item->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
+	graph_data->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
 
 	pptr = &item->parents;
 
@@ -759,8 +810,9 @@ static int fill_commit_in_graph(struct repository *r,
 
 static int find_commit_in_graph(struct commit *item, struct commit_graph *g, uint32_t *pos)
 {
-	if (item->graph_pos != COMMIT_NOT_FROM_GRAPH) {
-		*pos = item->graph_pos;
+	uint32_t graph_pos = commit_graph_position(item);
+	if (graph_pos != COMMIT_NOT_FROM_GRAPH) {
+		*pos = graph_pos;
 		return 1;
 	} else {
 		struct commit_graph *cur_g = g;
@@ -795,6 +847,14 @@ static int parse_commit_in_graph_one(struct repository *r,
 
 int parse_commit_in_graph(struct repository *r, struct commit *item)
 {
+	static int checked_env = 0;
+
+	if (!checked_env &&
+	    git_env_bool(GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE, 0))
+		die("dying as requested by the '%s' variable on commit-graph parse!",
+		    GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE);
+	checked_env = 1;
+
 	if (!prepare_commit_graph(r))
 		return 0;
 	return parse_commit_in_graph_one(r, r->objects->commit_graph, item);
@@ -815,12 +875,13 @@ static struct tree *load_tree_for_commit(struct repository *r,
 {
 	struct object_id oid;
 	const unsigned char *commit_data;
+	uint32_t graph_pos = commit_graph_position(c);
 
-	while (c->graph_pos < g->num_commits_in_base)
+	while (graph_pos < g->num_commits_in_base)
 		g = g->base_graph;
 
 	commit_data = g->chunk_commit_data +
-			GRAPH_DATA_WIDTH * (c->graph_pos - g->num_commits_in_base);
+			GRAPH_DATA_WIDTH * (graph_pos - g->num_commits_in_base);
 
 	hashcpy(oid.hash, commit_data);
 	set_commit_tree(c, lookup_tree(r, &oid));
@@ -834,7 +895,7 @@ static struct tree *get_commit_tree_in_graph_one(struct repository *r,
 {
 	if (c->maybe_tree)
 		return c->maybe_tree;
-	if (c->graph_pos == COMMIT_NOT_FROM_GRAPH)
+	if (commit_graph_position(c) == COMMIT_NOT_FROM_GRAPH)
 		BUG("get_commit_tree_in_graph_one called from non-commit-graph commit");
 
 	return load_tree_for_commit(r, g, (struct commit *)c);
@@ -881,16 +942,16 @@ struct write_commit_graph_context {
 	unsigned append:1,
 		 report_progress:1,
 		 split:1,
-		 check_oids:1,
 		 changed_paths:1,
 		 order_by_pack:1;
 
 	const struct split_commit_graph_opts *split_opts;
 	size_t total_bloom_filter_data_size;
+	const struct bloom_filter_settings *bloom_settings;
 };
 
-static void write_graph_chunk_fanout(struct hashfile *f,
-				     struct write_commit_graph_context *ctx)
+static int write_graph_chunk_fanout(struct hashfile *f,
+				    struct write_commit_graph_context *ctx)
 {
 	int i, count = 0;
 	struct commit **list = ctx->commits.list;
@@ -911,17 +972,21 @@ static void write_graph_chunk_fanout(struct hashfile *f,
 
 		hashwrite_be32(f, count);
 	}
+
+	return 0;
 }
 
-static void write_graph_chunk_oids(struct hashfile *f, int hash_len,
-				   struct write_commit_graph_context *ctx)
+static int write_graph_chunk_oids(struct hashfile *f,
+				  struct write_commit_graph_context *ctx)
 {
 	struct commit **list = ctx->commits.list;
 	int count;
 	for (count = 0; count < ctx->commits.nr; count++, list++) {
 		display_progress(ctx->progress, ++ctx->progress_cnt);
-		hashwrite(f, (*list)->object.oid.hash, (int)hash_len);
+		hashwrite(f, (*list)->object.oid.hash, the_hash_algo->rawsz);
 	}
+
+	return 0;
 }
 
 static const unsigned char *commit_to_sha1(size_t index, void *table)
@@ -930,8 +995,8 @@ static const unsigned char *commit_to_sha1(size_t index, void *table)
 	return commits[index]->object.oid.hash;
 }
 
-static void write_graph_chunk_data(struct hashfile *f, int hash_len,
-				   struct write_commit_graph_context *ctx)
+static int write_graph_chunk_data(struct hashfile *f,
+				  struct write_commit_graph_context *ctx)
 {
 	struct commit **list = ctx->commits.list;
 	struct commit **last = ctx->commits.list + ctx->commits.nr;
@@ -948,7 +1013,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 			die(_("unable to parse commit %s"),
 				oid_to_hex(&(*list)->object.oid));
 		tree = get_commit_tree_oid(*list);
-		hashwrite(f, tree->hash, hash_len);
+		hashwrite(f, tree->hash, the_hash_algo->rawsz);
 
 		parent = (*list)->parents;
 
@@ -1021,17 +1086,19 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 		else
 			packedDate[0] = 0;
 
-		packedDate[0] |= htonl((*list)->generation << 2);
+		packedDate[0] |= htonl(commit_graph_data_at(*list)->generation << 2);
 
 		packedDate[1] = htonl((*list)->date);
 		hashwrite(f, packedDate, 8);
 
 		list++;
 	}
+
+	return 0;
 }
 
-static void write_graph_chunk_extra_edges(struct hashfile *f,
-					  struct write_commit_graph_context *ctx)
+static int write_graph_chunk_extra_edges(struct hashfile *f,
+					 struct write_commit_graph_context *ctx)
 {
 	struct commit **list = ctx->commits.list;
 	struct commit **last = ctx->commits.list + ctx->commits.nr;
@@ -1080,59 +1147,67 @@ static void write_graph_chunk_extra_edges(struct hashfile *f,
 
 		list++;
 	}
+
+	return 0;
 }
 
-static void write_graph_chunk_bloom_indexes(struct hashfile *f,
-					    struct write_commit_graph_context *ctx)
+static int write_graph_chunk_bloom_indexes(struct hashfile *f,
+					   struct write_commit_graph_context *ctx)
 {
 	struct commit **list = ctx->commits.list;
 	struct commit **last = ctx->commits.list + ctx->commits.nr;
 	uint32_t cur_pos = 0;
-	struct progress *progress = NULL;
-	int i = 0;
-
-	if (ctx->report_progress)
-		progress = start_delayed_progress(
-			_("Writing changed paths Bloom filters index"),
-			ctx->commits.nr);
 
 	while (list < last) {
 		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
-		cur_pos += filter->len;
-		display_progress(progress, ++i);
+		size_t len = filter ? filter->len : 0;
+		cur_pos += len;
+		display_progress(ctx->progress, ++ctx->progress_cnt);
 		hashwrite_be32(f, cur_pos);
 		list++;
 	}
 
-	stop_progress(&progress);
+	return 0;
 }
 
-static void write_graph_chunk_bloom_data(struct hashfile *f,
-					 struct write_commit_graph_context *ctx,
-					 const struct bloom_filter_settings *settings)
+static void trace2_bloom_filter_settings(struct write_commit_graph_context *ctx)
+{
+	struct json_writer jw = JSON_WRITER_INIT;
+
+	jw_object_begin(&jw, 0);
+	jw_object_intmax(&jw, "hash_version", ctx->bloom_settings->hash_version);
+	jw_object_intmax(&jw, "num_hashes", ctx->bloom_settings->num_hashes);
+	jw_object_intmax(&jw, "bits_per_entry", ctx->bloom_settings->bits_per_entry);
+	jw_end(&jw);
+
+	trace2_data_json("bloom", ctx->r, "settings", &jw);
+
+	jw_release(&jw);
+}
+
+static int write_graph_chunk_bloom_data(struct hashfile *f,
+					struct write_commit_graph_context *ctx)
 {
 	struct commit **list = ctx->commits.list;
 	struct commit **last = ctx->commits.list + ctx->commits.nr;
-	struct progress *progress = NULL;
-	int i = 0;
 
-	if (ctx->report_progress)
-		progress = start_delayed_progress(
-			_("Writing changed paths Bloom filters data"),
-			ctx->commits.nr);
+	trace2_bloom_filter_settings(ctx);
 
-	hashwrite_be32(f, settings->hash_version);
-	hashwrite_be32(f, settings->num_hashes);
-	hashwrite_be32(f, settings->bits_per_entry);
+	hashwrite_be32(f, ctx->bloom_settings->hash_version);
+	hashwrite_be32(f, ctx->bloom_settings->num_hashes);
+	hashwrite_be32(f, ctx->bloom_settings->bits_per_entry);
 
 	while (list < last) {
 		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
-		display_progress(progress, ++i);
-		hashwrite(f, filter->data, filter->len * sizeof(unsigned char));
+		size_t len = filter ? filter->len : 0;
+
+		display_progress(ctx->progress, ++ctx->progress_cnt);
+		if (len)
+			hashwrite(f, filter->data, len * sizeof(unsigned char));
 		list++;
 	}
 
-	stop_progress(&progress);
+	return 0;
 }
 
 static int oid_compare(const void *_a, const void *_b)
@@ -1220,7 +1295,7 @@ static void close_reachable(struct write_commit_graph_context *ctx)
 			continue;
 		if (ctx->split) {
 			if ((!parse_commit(commit) &&
-			     commit->graph_pos == COMMIT_NOT_FROM_GRAPH) ||
+			     commit_graph_position(commit) == COMMIT_NOT_FROM_GRAPH) ||
 			    flags == COMMIT_GRAPH_SPLIT_REPLACE)
 				add_missing_parents(ctx, commit);
 		} else if (!parse_commit_no_graph(commit))
@@ -1252,9 +1327,11 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 					_("Computing commit graph generation numbers"),
 					ctx->commits.nr);
 	for (i = 0; i < ctx->commits.nr; i++) {
+		uint32_t generation = commit_graph_data_at(ctx->commits.list[i])->generation;
+
 		display_progress(ctx->progress, i + 1);
-		if (ctx->commits.list[i]->generation != GENERATION_NUMBER_INFINITY &&
-		    ctx->commits.list[i]->generation != GENERATION_NUMBER_ZERO)
+		if (generation != GENERATION_NUMBER_INFINITY &&
+		    generation != GENERATION_NUMBER_ZERO)
 			continue;
 
 		commit_list_insert(ctx->commits.list[i], &list);
@@ -1265,22 +1342,26 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 			uint32_t max_generation = 0;
 
 			for (parent = current->parents; parent; parent = parent->next) {
-				if (parent->item->generation == GENERATION_NUMBER_INFINITY ||
-				    parent->item->generation == GENERATION_NUMBER_ZERO) {
+				generation = commit_graph_data_at(parent->item)->generation;
+
+				if (generation == GENERATION_NUMBER_INFINITY ||
+				    generation == GENERATION_NUMBER_ZERO) {
 					all_parents_computed = 0;
 					commit_list_insert(parent->item, &list);
 					break;
-				} else if (parent->item->generation > max_generation) {
-					max_generation = parent->item->generation;
+				} else if (generation > max_generation) {
+					max_generation = generation;
 				}
 			}
 
 			if (all_parents_computed) {
-				current->generation = max_generation + 1;
+				struct commit_graph_data *data = commit_graph_data_at(current);
+
+				data->generation = max_generation + 1;
 				pop_commit(&list);
 
-				if (current->generation > GENERATION_NUMBER_MAX)
-					current->generation = GENERATION_NUMBER_MAX;
+				if (data->generation > GENERATION_NUMBER_MAX)
+					data->generation = GENERATION_NUMBER_MAX;
 			}
 		}
 	}
@@ -1319,13 +1400,25 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 	stop_progress(&progress);
 }
 
+struct refs_cb_data {
+	struct oidset *commits;
+	struct progress *progress;
+};
+
 static int add_ref_to_set(const char *refname,
 			  const struct object_id *oid,
 			  int flags, void *cb_data)
 {
-	struct oidset *commits = (struct oidset *)cb_data;
+	struct object_id peeled;
+	struct refs_cb_data *data = (struct refs_cb_data *)cb_data;
+
+	if (!peel_ref(refname, &peeled))
+		oid = &peeled;
+	if (oid_object_info(the_repository, oid, NULL) == OBJ_COMMIT)
+		oidset_insert(data->commits, oid);
+
+	display_progress(data->progress, oidset_size(data->commits));
 
-	oidset_insert(commits, oid);
 	return 0;
 }
 
@@ -1334,9 +1427,19 @@ int write_commit_graph_reachable(struct object_directory *odb,
 				 const struct split_commit_graph_opts *split_opts)
 {
 	struct oidset commits = OIDSET_INIT;
+	struct refs_cb_data data;
 	int result;
 
-	for_each_ref(add_ref_to_set, &commits);
+	memset(&data, 0, sizeof(data));
+	data.commits = &commits;
+	if (flags & COMMIT_GRAPH_WRITE_PROGRESS)
+		data.progress = start_delayed_progress(
+			_("Collecting referenced commits"), 0);
+
+	for_each_ref(add_ref_to_set, &data);
+
+	stop_progress(&data.progress);
+
 	result = write_commit_graph(odb, NULL, &commits,
 				    flags, split_opts);
 
@@ -1392,46 +1495,19 @@ static int fill_oids_from_packs(struct write_commit_graph_context *ctx,
 static int fill_oids_from_commits(struct write_commit_graph_context *ctx,
 				  struct oidset *commits)
 {
-	uint32_t i = 0;
-	struct strbuf progress_title = STRBUF_INIT;
 	struct oidset_iter iter;
 	struct object_id *oid;
 
 	if (!oidset_size(commits))
 		return 0;
 
-	if (ctx->report_progress) {
-		strbuf_addf(&progress_title,
-			    Q_("Finding commits for commit graph from %d ref",
-			       "Finding commits for commit graph from %d refs",
-			       oidset_size(commits)),
-			    oidset_size(commits));
-		ctx->progress = start_delayed_progress(
-					progress_title.buf,
-					oidset_size(commits));
-	}
-
 	oidset_iter_init(commits, &iter);
 	while ((oid = oidset_iter_next(&iter))) {
-		struct commit *result;
-
-		display_progress(ctx->progress, ++i);
-
-		result = lookup_commit_reference_gently(ctx->r, oid, 1);
-		if (result) {
-			ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc);
-			oidcpy(&ctx->oids.list[ctx->oids.nr], &(result->object.oid));
-			ctx->oids.nr++;
-		} else if (ctx->check_oids) {
-			error(_("invalid commit object id: %s"),
-			      oid_to_hex(oid));
-			return -1;
-		}
+		ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc);
+		oidcpy(&ctx->oids.list[ctx->oids.nr], oid);
+		ctx->oids.nr++;
 	}
 
-	stop_progress(&ctx->progress);
-	strbuf_release(&progress_title);
-
 	return 0;
 }
 
@@ -1465,7 +1541,7 @@ static uint32_t count_distinct_commits(struct write_commit_graph_context *ctx)
 			if (ctx->split) {
 				struct commit *c = lookup_commit(ctx->r, &ctx->oids.list[i]);
 
-				if (!c || c->graph_pos != COMMIT_NOT_FROM_GRAPH)
+				if (!c || commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH)
 					continue;
 			}
 
@@ -1499,7 +1575,7 @@ static void copy_oids_to_commits(struct write_commit_graph_context *ctx)
 		ctx->commits.list[ctx->commits.nr] = lookup_commit(ctx->r, &ctx->oids.list[i]);
 
 		if (ctx->split && flags != COMMIT_GRAPH_SPLIT_REPLACE &&
-		    ctx->commits.list[ctx->commits.nr]->graph_pos != COMMIT_NOT_FROM_GRAPH)
+		    commit_graph_position(ctx->commits.list[ctx->commits.nr]) != COMMIT_NOT_FROM_GRAPH)
 			continue;
 
 		if (ctx->split && flags == COMMIT_GRAPH_SPLIT_REPLACE)
@@ -1542,19 +1618,36 @@ static int write_graph_chunk_base(struct hashfile *f,
 	return 0;
 }
 
+typedef int (*chunk_write_fn)(struct hashfile *f,
+			      struct write_commit_graph_context *ctx);
+
+struct chunk_info {
+	uint32_t id;
+	uint64_t size;
+	chunk_write_fn write_fn;
+};
+
 static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 {
 	uint32_t i;
 	int fd;
 	struct hashfile *f;
 	struct lock_file lk = LOCK_INIT;
-	uint32_t chunk_ids[MAX_NUM_CHUNKS + 1];
-	uint64_t chunk_offsets[MAX_NUM_CHUNKS + 1];
+	struct chunk_info chunks[MAX_NUM_CHUNKS + 1];
 	const unsigned hashsz = the_hash_algo->rawsz;
 	struct strbuf progress_title = STRBUF_INIT;
 	int num_chunks = 3;
+	uint64_t chunk_offset;
 	struct object_id file_hash;
-	const struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
+	struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
+
+	if (!ctx->bloom_settings) {
+		bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY",
+							      bloom_settings.bits_per_entry);
+		bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES",
+							  bloom_settings.num_hashes);
+		ctx->bloom_settings = &bloom_settings;
+	}
 
 	if (ctx->split) {
 		struct strbuf tmp_file = STRBUF_INIT;
@@ -1600,51 +1693,41 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 		f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf);
 	}
 
-	chunk_ids[0] = GRAPH_CHUNKID_OIDFANOUT;
-	chunk_ids[1] = GRAPH_CHUNKID_OIDLOOKUP;
-	chunk_ids[2] = GRAPH_CHUNKID_DATA;
+	chunks[0].id = GRAPH_CHUNKID_OIDFANOUT;
+	chunks[0].size = GRAPH_FANOUT_SIZE;
+	chunks[0].write_fn = write_graph_chunk_fanout;
+	chunks[1].id = GRAPH_CHUNKID_OIDLOOKUP;
+	chunks[1].size = hashsz * ctx->commits.nr;
+	chunks[1].write_fn = write_graph_chunk_oids;
+	chunks[2].id = GRAPH_CHUNKID_DATA;
+	chunks[2].size = (hashsz + 16) * ctx->commits.nr;
+	chunks[2].write_fn = write_graph_chunk_data;
 	if (ctx->num_extra_edges) {
-		chunk_ids[num_chunks] = GRAPH_CHUNKID_EXTRAEDGES;
+		chunks[num_chunks].id = GRAPH_CHUNKID_EXTRAEDGES;
+		chunks[num_chunks].size = 4 * ctx->num_extra_edges;
+		chunks[num_chunks].write_fn = write_graph_chunk_extra_edges;
 		num_chunks++;
 	}
 	if (ctx->changed_paths) {
-		chunk_ids[num_chunks] = GRAPH_CHUNKID_BLOOMINDEXES;
+		chunks[num_chunks].id = GRAPH_CHUNKID_BLOOMINDEXES;
+		chunks[num_chunks].size = sizeof(uint32_t) * ctx->commits.nr;
+		chunks[num_chunks].write_fn = write_graph_chunk_bloom_indexes;
 		num_chunks++;
-		chunk_ids[num_chunks] = GRAPH_CHUNKID_BLOOMDATA;
+		chunks[num_chunks].id = GRAPH_CHUNKID_BLOOMDATA;
+		chunks[num_chunks].size = sizeof(uint32_t) * 3
+					  + ctx->total_bloom_filter_data_size;
+		chunks[num_chunks].write_fn = write_graph_chunk_bloom_data;
 		num_chunks++;
 	}
 	if (ctx->num_commit_graphs_after > 1) {
-		chunk_ids[num_chunks] = GRAPH_CHUNKID_BASE;
+		chunks[num_chunks].id = GRAPH_CHUNKID_BASE;
+		chunks[num_chunks].size = hashsz * (ctx->num_commit_graphs_after - 1);
+		chunks[num_chunks].write_fn = write_graph_chunk_base;
 		num_chunks++;
 	}
 
-	chunk_ids[num_chunks] = 0;
-
-	chunk_offsets[0] = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH;
-	chunk_offsets[1] = chunk_offsets[0] + GRAPH_FANOUT_SIZE;
-	chunk_offsets[2] = chunk_offsets[1] + hashsz * ctx->commits.nr;
-	chunk_offsets[3] = chunk_offsets[2] + (hashsz + 16) * ctx->commits.nr;
-
-	num_chunks = 3;
-	if (ctx->num_extra_edges) {
-		chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] +
-						4 * ctx->num_extra_edges;
-		num_chunks++;
-	}
-	if (ctx->changed_paths) {
-		chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] +
-						sizeof(uint32_t) * ctx->commits.nr;
-		num_chunks++;
-
-		chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] +
-						sizeof(uint32_t) * 3 + ctx->total_bloom_filter_data_size;
-		num_chunks++;
-	}
-	if (ctx->num_commit_graphs_after > 1) {
-		chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] +
-						hashsz * (ctx->num_commit_graphs_after - 1);
-		num_chunks++;
-	}
+	chunks[num_chunks].id = 0;
+	chunks[num_chunks].size = 0;
 
 	hashwrite_be32(f, GRAPH_SIGNATURE);
 
@@ -1653,13 +1736,16 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	hashwrite_u8(f, num_chunks);
 	hashwrite_u8(f, ctx->num_commit_graphs_after - 1);
 
+	chunk_offset = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH;
 	for (i = 0; i <= num_chunks; i++) {
 		uint32_t chunk_write[3];
 
-		chunk_write[0] = htonl(chunk_ids[i]);
-		chunk_write[1] = htonl(chunk_offsets[i] >> 32);
-		chunk_write[2] = htonl(chunk_offsets[i] & 0xffffffff);
+		chunk_write[0] = htonl(chunks[i].id);
+		chunk_write[1] = htonl(chunk_offset >> 32);
+		chunk_write[2] = htonl(chunk_offset & 0xffffffff);
 		hashwrite(f, chunk_write, 12);
+
+		chunk_offset += chunks[i].size;
 	}
 
 	if (ctx->report_progress) {
@@ -1672,19 +1758,19 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 			progress_title.buf,
 			num_chunks * ctx->commits.nr);
 	}
-	write_graph_chunk_fanout(f, ctx);
-	write_graph_chunk_oids(f, hashsz, ctx);
-	write_graph_chunk_data(f, hashsz, ctx);
-	if (ctx->num_extra_edges)
-		write_graph_chunk_extra_edges(f, ctx);
-	if (ctx->changed_paths) {
-		write_graph_chunk_bloom_indexes(f, ctx);
-		write_graph_chunk_bloom_data(f, ctx, &bloom_settings);
-	}
-	if (ctx->num_commit_graphs_after > 1 &&
-	    write_graph_chunk_base(f, ctx)) {
-		return -1;
+
+	for (i = 0; i < num_chunks; i++) {
+		uint64_t start_offset = f->total + f->offset;
+
+		if (chunks[i].write_fn(f, ctx))
+			return -1;
+
+		if (f->total + f->offset != start_offset + chunks[i].size)
+			BUG("expected to write %"PRId64" bytes to chunk %"PRIx32", but wrote %"PRId64" instead",
+			    chunks[i].size, chunks[i].id,
+			    f->total + f->offset - start_offset);
 	}
+
 	stop_progress(&ctx->progress);
 	strbuf_release(&progress_title);
 
@@ -2017,11 +2103,24 @@ int write_commit_graph(struct object_directory *odb,
 	ctx->append = flags & COMMIT_GRAPH_WRITE_APPEND ? 1 : 0;
 	ctx->report_progress = flags & COMMIT_GRAPH_WRITE_PROGRESS ? 1 : 0;
 	ctx->split = flags & COMMIT_GRAPH_WRITE_SPLIT ? 1 : 0;
-	ctx->check_oids = flags & COMMIT_GRAPH_WRITE_CHECK_OIDS ? 1 : 0;
 	ctx->split_opts = split_opts;
-	ctx->changed_paths = flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS ? 1 : 0;
 	ctx->total_bloom_filter_data_size = 0;
 
+	if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS)
+		ctx->changed_paths = 1;
+	if (!(flags & COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS)) {
+		struct commit_graph *g;
+		prepare_commit_graph_one(ctx->r, ctx->odb);
+
+		g = ctx->r->objects->commit_graph;
+
+		/* We have changed-paths already. Keep them in the next graph */
+		if (g && g->chunk_bloom_data) {
+			ctx->changed_paths = 1;
+			ctx->bloom_settings = g->bloom_filter_settings;
+		}
+	}
+
 	if (ctx->split) {
 		struct commit_graph *g;
 		prepare_commit_graph(ctx->r);
@@ -2249,6 +2348,7 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags)
 		struct commit *graph_commit, *odb_commit;
 		struct commit_list *graph_parents, *odb_parents;
 		uint32_t max_generation = 0;
+		uint32_t generation;
 
 		display_progress(progress, i + 1);
 		hashcpy(cur_oid.hash, g->chunk_oid_lookup + g->hash_len * i);
@@ -2287,8 +2387,9 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags)
 					     oid_to_hex(&graph_parents->item->object.oid),
 					     oid_to_hex(&odb_parents->item->object.oid));
 
-			if (graph_parents->item->generation > max_generation)
-				max_generation = graph_parents->item->generation;
+			generation = commit_graph_generation(graph_parents->item);
+			if (generation > max_generation)
+				max_generation = generation;
 
 			graph_parents = graph_parents->next;
 			odb_parents = odb_parents->next;
@@ -2298,7 +2399,7 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags)
 			graph_report(_("commit-graph parent list for commit %s terminates early"),
 				     oid_to_hex(&cur_oid));
 
-		if (!graph_commit->generation) {
+		if (!commit_graph_generation(graph_commit)) {
 			if (generation_zero == GENERATION_NUMBER_EXISTS)
 				graph_report(_("commit-graph has generation number zero for commit %s, but non-zero elsewhere"),
 					     oid_to_hex(&cur_oid));
@@ -2318,10 +2419,11 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags)
 		if (max_generation == GENERATION_NUMBER_MAX)
 			max_generation--;
 
-		if (graph_commit->generation != max_generation + 1)
+		generation = commit_graph_generation(graph_commit);
+		if (generation != max_generation + 1)
 			graph_report(_("commit-graph generation for commit %s is %u != %u"),
 				     oid_to_hex(&cur_oid),
-				     graph_commit->generation,
+				     generation,
 				     max_generation + 1);
 
 		if (graph_commit->date != odb_commit->date)