1 files changed, 442 insertions, 124 deletions

diff --git a/commit-graph.c b/commit-graph.c
index f013a84e29..fdd1c4fa7c 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -16,13 +16,33 @@
 #include "hashmap.h"
 #include "replace-object.h"
 #include "progress.h"
+#include "bloom.h"
+#include "commit-slab.h"
+#include "shallow.h"
+
+void git_test_write_commit_graph_or_die(void)
+{
+	int flags = 0;
+	if (!git_env_bool(GIT_TEST_COMMIT_GRAPH, 0))
+		return;
+
+	if (git_env_bool(GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS, 0))
+		flags = COMMIT_GRAPH_WRITE_BLOOM_FILTERS;
+
+	if (write_commit_graph_reachable(the_repository->objects->odb,
+					 flags, NULL))
+		die("failed to write commit-graph under GIT_TEST_COMMIT_GRAPH");
+}
 
 #define GRAPH_SIGNATURE 0x43475048 /* "CGPH" */
 #define GRAPH_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */
 #define GRAPH_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */
 #define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */
 #define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
+#define GRAPH_CHUNKID_BLOOMINDEXES 0x42494458 /* "BIDX" */
+#define GRAPH_CHUNKID_BLOOMDATA 0x42444154 /* "BDAT" */
 #define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */
+#define MAX_NUM_CHUNKS 7
 
 #define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
 
@@ -44,9 +64,105 @@
 /* Remember to update object flag allocation in object.h */
 #define REACHABLE       (1u<<15)
 
-char *get_commit_graph_filename(struct object_directory *odb)
+/* Keep track of the order in which commits are added to our list. */
+define_commit_slab(commit_pos, int);
+static struct commit_pos commit_pos = COMMIT_SLAB_INIT(1, commit_pos);
+
+static void set_commit_pos(struct repository *r, const struct object_id *oid)
+{
+	static int32_t max_pos;
+	struct commit *commit = lookup_commit(r, oid);
+
+	if (!commit)
+		return; /* should never happen, but be lenient */
+
+	*commit_pos_at(&commit_pos, commit) = max_pos++;
+}
+
+static int commit_pos_cmp(const void *va, const void *vb)
+{
+	const struct commit *a = *(const struct commit **)va;
+	const struct commit *b = *(const struct commit **)vb;
+	return commit_pos_at(&commit_pos, a) -
+	       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)
 {
-	return xstrfmt("%s/info/commit-graph", odb->path);
+	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 (generation_a < generation_b)
+		return -1;
+	else if (generation_a > generation_b)
+		return 1;
+
+	/* use date as a heuristic when generations are equal */
+	if (a->date < b->date)
+		return -1;
+	else if (a->date > b->date)
+		return 1;
+	return 0;
+}
+
+char *get_commit_graph_filename(struct object_directory *obj_dir)
+{
+	return xstrfmt("%s/info/commit-graph", obj_dir->path);
 }
 
 static char *get_split_graph_filename(struct object_directory *odb,
@@ -69,7 +185,6 @@ static uint8_t oid_version(void)
 static struct commit_graph *alloc_commit_graph(void)
 {
 	struct commit_graph *g = xcalloc(1, sizeof(*g));
-	g->graph_fd = -1;
 
 	return g;
 }
@@ -123,14 +238,13 @@ struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st,
 		return NULL;
 	}
 	graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0);
-	ret = parse_commit_graph(graph_map, fd, graph_size);
+	close(fd);
+	ret = parse_commit_graph(graph_map, graph_size);
 
 	if (ret)
 		ret->odb = odb;
-	else {
+	else
 		munmap(graph_map, graph_size);
-		close(fd);
-	}
 
 	return ret;
 }
@@ -165,8 +279,7 @@ static int verify_commit_graph_lite(struct commit_graph *g)
 	return 0;
 }
 
-struct commit_graph *parse_commit_graph(void *graph_map, int fd,
-					size_t graph_size)
+struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
 {
 	const unsigned char *data, *chunk_lookup;
 	uint32_t i;
@@ -209,7 +322,6 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 
 	graph->hash_len = the_hash_algo->rawsz;
 	graph->num_chunks = *(unsigned char*)(data + 6);
-	graph->graph_fd = fd;
 	graph->data = graph_map;
 	graph->data_len = graph_size;
 
@@ -224,8 +336,7 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 		if (data + graph_size - chunk_lookup <
 		    GRAPH_CHUNKLOOKUP_WIDTH) {
 			error(_("commit-graph chunk lookup table entry missing; file may be incomplete"));
-			free(graph);
-			return NULL;
+			goto free_and_return;
 		}
 
 		chunk_id = get_be32(chunk_lookup + 0);
@@ -236,8 +347,7 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 		if (chunk_offset > graph_size - the_hash_algo->rawsz) {
 			error(_("commit-graph improper chunk offset %08x%08x"), (uint32_t)(chunk_offset >> 32),
 			      (uint32_t)chunk_offset);
-			free(graph);
-			return NULL;
+			goto free_and_return;
 		}
 
 		switch (chunk_id) {
@@ -274,12 +384,37 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 				chunk_repeated = 1;
 			else
 				graph->chunk_base_graphs = data + chunk_offset;
+			break;
+
+		case GRAPH_CHUNKID_BLOOMINDEXES:
+			if (graph->chunk_bloom_indexes)
+				chunk_repeated = 1;
+			else
+				graph->chunk_bloom_indexes = data + chunk_offset;
+			break;
+
+		case GRAPH_CHUNKID_BLOOMDATA:
+			if (graph->chunk_bloom_data)
+				chunk_repeated = 1;
+			else {
+				uint32_t hash_version;
+				graph->chunk_bloom_data = data + chunk_offset;
+				hash_version = get_be32(data + chunk_offset);
+
+				if (hash_version != 1)
+					break;
+
+				graph->bloom_filter_settings = xmalloc(sizeof(struct bloom_filter_settings));
+				graph->bloom_filter_settings->hash_version = hash_version;
+				graph->bloom_filter_settings->num_hashes = get_be32(data + chunk_offset + 4);
+				graph->bloom_filter_settings->bits_per_entry = get_be32(data + chunk_offset + 8);
+			}
+			break;
 		}
 
 		if (chunk_repeated) {
 			error(_("commit-graph chunk id %08x appears multiple times"), chunk_id);
-			free(graph);
-			return NULL;
+			goto free_and_return;
 		}
 
 		if (last_chunk_id == GRAPH_CHUNKID_OIDLOOKUP)
@@ -292,14 +427,26 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 		last_chunk_offset = chunk_offset;
 	}
 
+	if (graph->chunk_bloom_indexes && graph->chunk_bloom_data) {
+		init_bloom_filters();
+	} else {
+		/* We need both the bloom chunks to exist together. Else ignore the data */
+		graph->chunk_bloom_indexes = NULL;
+		graph->chunk_bloom_data = NULL;
+		FREE_AND_NULL(graph->bloom_filter_settings);
+	}
+
 	hashcpy(graph->oid.hash, graph->data + graph->data_len - graph->hash_len);
 
-	if (verify_commit_graph_lite(graph)) {
-		free(graph);
-		return NULL;
-	}
+	if (verify_commit_graph_lite(graph))
+		goto free_and_return;
 
 	return graph;
+
+free_and_return:
+	free(graph->bloom_filter_settings);
+	free(graph);
+	return NULL;
 }
 
 static struct commit_graph *load_commit_graph_one(const char *graph_file,
@@ -577,13 +724,14 @@ 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)
@@ -591,8 +739,10 @@ 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)
@@ -608,6 +758,7 @@ 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;
 
@@ -621,7 +772,8 @@ 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;
@@ -634,7 +786,7 @@ 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;
 
@@ -666,8 +818,9 @@ 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;
@@ -722,12 +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));
@@ -741,7 +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);
@@ -788,9 +942,11 @@ 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;
 };
 
 static void write_graph_chunk_fanout(struct hashfile *f,
@@ -866,7 +1022,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 
 			if (edge_value >= 0)
 				edge_value += ctx->new_num_commits_in_base;
-			else {
+			else if (ctx->new_base_graph) {
 				uint32_t pos;
 				if (find_commit_in_graph(parent->item,
 							 ctx->new_base_graph,
@@ -897,7 +1053,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 
 			if (edge_value >= 0)
 				edge_value += ctx->new_num_commits_in_base;
-			else {
+			else if (ctx->new_base_graph) {
 				uint32_t pos;
 				if (find_commit_in_graph(parent->item,
 							 ctx->new_base_graph,
@@ -925,7 +1081,7 @@ 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);
@@ -964,7 +1120,7 @@ static void write_graph_chunk_extra_edges(struct hashfile *f,
 
 			if (edge_value >= 0)
 				edge_value += ctx->new_num_commits_in_base;
-			else {
+			else if (ctx->new_base_graph) {
 				uint32_t pos;
 				if (find_commit_in_graph(parent->item,
 							 ctx->new_base_graph,
@@ -986,6 +1142,59 @@ static void write_graph_chunk_extra_edges(struct hashfile *f,
 	}
 }
 
+static void 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);
+		hashwrite_be32(f, cur_pos);
+		list++;
+	}
+
+	stop_progress(&progress);
+}
+
+static void write_graph_chunk_bloom_data(struct hashfile *f,
+					 struct write_commit_graph_context *ctx,
+					 const struct bloom_filter_settings *settings)
+{
+	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);
+
+	hashwrite_be32(f, settings->hash_version);
+	hashwrite_be32(f, settings->num_hashes);
+	hashwrite_be32(f, 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));
+		list++;
+	}
+
+	stop_progress(&progress);
+}
+
 static int oid_compare(const void *_a, const void *_b)
 {
 	const struct object_id *a = (const struct object_id *)_a;
@@ -1017,6 +1226,8 @@ static int add_packed_commits(const struct object_id *oid,
 	oidcpy(&(ctx->oids.list[ctx->oids.nr]), oid);
 	ctx->oids.nr++;
 
+	set_commit_pos(ctx->r, oid);
+
 	return 0;
 }
 
@@ -1037,6 +1248,8 @@ static void close_reachable(struct write_commit_graph_context *ctx)
 {
 	int i;
 	struct commit *commit;
+	enum commit_graph_split_flags flags = ctx->split_opts ?
+		ctx->split_opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	if (ctx->report_progress)
 		ctx->progress = start_delayed_progress(
@@ -1066,8 +1279,9 @@ static void close_reachable(struct write_commit_graph_context *ctx)
 		if (!commit)
 			continue;
 		if (ctx->split) {
-			if (!parse_commit(commit) &&
-			    commit->graph_pos == COMMIT_NOT_FROM_GRAPH)
+			if ((!parse_commit(commit) &&
+			     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))
 			add_missing_parents(ctx, commit);
@@ -1098,9 +1312,11 @@ 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);
@@ -1111,35 +1327,83 @@ 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;
 			}
 		}
 	}
 	stop_progress(&ctx->progress);
 }
 
-static int add_ref_to_list(const char *refname,
-			   const struct object_id *oid,
-			   int flags, void *cb_data)
+static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 {
-	struct string_list *list = (struct string_list *)cb_data;
+	int i;
+	struct progress *progress = NULL;
+	struct commit **sorted_commits;
+
+	init_bloom_filters();
+
+	if (ctx->report_progress)
+		progress = start_delayed_progress(
+			_("Computing commit changed paths Bloom filters"),
+			ctx->commits.nr);
+
+	ALLOC_ARRAY(sorted_commits, ctx->commits.nr);
+	COPY_ARRAY(sorted_commits, ctx->commits.list, ctx->commits.nr);
+
+	if (ctx->order_by_pack)
+		QSORT(sorted_commits, ctx->commits.nr, commit_pos_cmp);
+	else
+		QSORT(sorted_commits, ctx->commits.nr, commit_gen_cmp);
+
+	for (i = 0; i < ctx->commits.nr; i++) {
+		struct commit *c = sorted_commits[i];
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, c, 1);
+		ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
+		display_progress(progress, i + 1);
+	}
+
+	free(sorted_commits);
+	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 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));
 
-	string_list_append(list, oid_to_hex(oid));
 	return 0;
 }
 
@@ -1147,14 +1411,23 @@ int write_commit_graph_reachable(struct object_directory *odb,
 				 enum commit_graph_write_flags flags,
 				 const struct split_commit_graph_opts *split_opts)
 {
-	struct string_list list = STRING_LIST_INIT_DUP;
+	struct oidset commits = OIDSET_INIT;
+	struct refs_cb_data data;
 	int result;
 
-	for_each_ref(add_ref_to_list, &list);
-	result = write_commit_graph(odb, NULL, &list,
+	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);
+	result = write_commit_graph(odb, NULL, &commits,
 				    flags, split_opts);
 
-	string_list_clear(&list, 0);
+	oidset_clear(&commits);
+	if (data.progress)
+		stop_progress(&data.progress);
 	return result;
 }
 
@@ -1203,41 +1476,21 @@ static int fill_oids_from_packs(struct write_commit_graph_context *ctx,
 	return 0;
 }
 
-static int fill_oids_from_commit_hex(struct write_commit_graph_context *ctx,
-				     struct string_list *commit_hex)
+static int fill_oids_from_commits(struct write_commit_graph_context *ctx,
+				  struct oidset *commits)
 {
-	uint32_t i;
-	struct strbuf progress_title = STRBUF_INIT;
+	struct oidset_iter iter;
+	struct object_id *oid;
 
-	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",
-			       commit_hex->nr),
-			    commit_hex->nr);
-		ctx->progress = start_delayed_progress(
-					progress_title.buf,
-					commit_hex->nr);
-	}
-	for (i = 0; i < commit_hex->nr; i++) {
-		const char *end;
-		struct object_id oid;
-		struct commit *result;
+	if (!oidset_size(commits))
+		return 0;
 
-		display_progress(ctx->progress, i + 1);
-		if (!parse_oid_hex(commit_hex->items[i].string, &oid, &end) &&
-		    (result = lookup_commit_reference_gently(ctx->r, &oid, 1))) {
-			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"),
-			    commit_hex->items[i].string);
-			return -1;
-		}
+	oidset_iter_init(commits, &iter);
+	while ((oid = oidset_iter_next(&iter))) {
+		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;
 }
@@ -1272,7 +1525,7 @@ 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;
 			}
 
@@ -1287,6 +1540,8 @@ static uint32_t count_distinct_commits(struct write_commit_graph_context *ctx)
 static void copy_oids_to_commits(struct write_commit_graph_context *ctx)
 {
 	uint32_t i;
+	enum commit_graph_split_flags flags = ctx->split_opts ?
+		ctx->split_opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	ctx->num_extra_edges = 0;
 	if (ctx->report_progress)
@@ -1303,11 +1558,14 @@ static void copy_oids_to_commits(struct write_commit_graph_context *ctx)
 		ALLOC_GROW(ctx->commits.list, ctx->commits.nr + 1, ctx->commits.alloc);
 		ctx->commits.list[ctx->commits.nr] = lookup_commit(ctx->r, &ctx->oids.list[i]);
 
-		if (ctx->split &&
-		    ctx->commits.list[ctx->commits.nr]->graph_pos != COMMIT_NOT_FROM_GRAPH)
+		if (ctx->split && flags != COMMIT_GRAPH_SPLIT_REPLACE &&
+		    commit_graph_position(ctx->commits.list[ctx->commits.nr]) != COMMIT_NOT_FROM_GRAPH)
 			continue;
 
-		parse_commit_no_graph(ctx->commits.list[ctx->commits.nr]);
+		if (ctx->split && flags == COMMIT_GRAPH_SPLIT_REPLACE)
+			parse_commit(ctx->commits.list[ctx->commits.nr]);
+		else
+			parse_commit_no_graph(ctx->commits.list[ctx->commits.nr]);
 
 		num_parents = commit_list_count(ctx->commits.list[ctx->commits.nr]->parents);
 		if (num_parents > 2)
@@ -1350,12 +1608,13 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	int fd;
 	struct hashfile *f;
 	struct lock_file lk = LOCK_INIT;
-	uint32_t chunk_ids[6];
-	uint64_t chunk_offsets[6];
+	uint32_t chunk_ids[MAX_NUM_CHUNKS + 1];
+	uint64_t chunk_offsets[MAX_NUM_CHUNKS + 1];
 	const unsigned hashsz = the_hash_algo->rawsz;
 	struct strbuf progress_title = STRBUF_INIT;
 	int num_chunks = 3;
 	struct object_id file_hash;
+	const struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
 
 	if (ctx->split) {
 		struct strbuf tmp_file = STRBUF_INIT;
@@ -1378,17 +1637,25 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	if (ctx->split) {
 		char *lock_name = get_chain_filename(ctx->odb);
 
-		hold_lock_file_for_update(&lk, lock_name, LOCK_DIE_ON_ERROR);
+		hold_lock_file_for_update_mode(&lk, lock_name,
+					       LOCK_DIE_ON_ERROR, 0444);
 
 		fd = git_mkstemp_mode(ctx->graph_name, 0444);
 		if (fd < 0) {
-			error(_("unable to create '%s'"), ctx->graph_name);
+			error(_("unable to create temporary graph layer"));
+			return -1;
+		}
+
+		if (adjust_shared_perm(ctx->graph_name)) {
+			error(_("unable to adjust shared permissions for '%s'"),
+			      ctx->graph_name);
 			return -1;
 		}
 
 		f = hashfd(fd, ctx->graph_name);
 	} else {
-		hold_lock_file_for_update(&lk, ctx->graph_name, LOCK_DIE_ON_ERROR);
+		hold_lock_file_for_update_mode(&lk, ctx->graph_name,
+					       LOCK_DIE_ON_ERROR, 0444);
 		fd = lk.tempfile->fd;
 		f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf);
 	}
@@ -1400,6 +1667,12 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 		chunk_ids[num_chunks] = GRAPH_CHUNKID_EXTRAEDGES;
 		num_chunks++;
 	}
+	if (ctx->changed_paths) {
+		chunk_ids[num_chunks] = GRAPH_CHUNKID_BLOOMINDEXES;
+		num_chunks++;
+		chunk_ids[num_chunks] = GRAPH_CHUNKID_BLOOMDATA;
+		num_chunks++;
+	}
 	if (ctx->num_commit_graphs_after > 1) {
 		chunk_ids[num_chunks] = GRAPH_CHUNKID_BASE;
 		num_chunks++;
@@ -1418,6 +1691,15 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 						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);
@@ -1455,6 +1737,10 @@ static int write_commit_graph_file(struct write_commit_graph_context *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;
@@ -1488,8 +1774,12 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 		}
 
 		if (ctx->base_graph_name) {
-			const char *dest = ctx->commit_graph_filenames_after[
-						ctx->num_commit_graphs_after - 2];
+			const char *dest;
+			int idx = ctx->num_commit_graphs_after - 1;
+			if (ctx->num_commit_graphs_after > 1)
+				idx--;
+
+			dest = ctx->commit_graph_filenames_after[idx];
 
 			if (strcmp(ctx->base_graph_name, dest)) {
 				result = rename(ctx->base_graph_name, dest);
@@ -1529,6 +1819,7 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 {
 	struct commit_graph *g;
 	uint32_t num_commits;
+	enum commit_graph_split_flags flags = COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 	uint32_t i;
 
 	int max_commits = 0;
@@ -1539,24 +1830,36 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 
 		if (ctx->split_opts->size_multiple)
 			size_mult = ctx->split_opts->size_multiple;
+
+		flags = ctx->split_opts->flags;
 	}
 
 	g = ctx->r->objects->commit_graph;
 	num_commits = ctx->commits.nr;
-	ctx->num_commit_graphs_after = ctx->num_commit_graphs_before + 1;
-
-	while (g && (g->num_commits <= size_mult * num_commits ||
-		    (max_commits && num_commits > max_commits))) {
-		if (g->odb != ctx->odb)
-			break;
+	if (flags == COMMIT_GRAPH_SPLIT_REPLACE)
+		ctx->num_commit_graphs_after = 1;
+	else
+		ctx->num_commit_graphs_after = ctx->num_commit_graphs_before + 1;
+
+	if (flags != COMMIT_GRAPH_SPLIT_MERGE_PROHIBITED &&
+	    flags != COMMIT_GRAPH_SPLIT_REPLACE) {
+		while (g && (g->num_commits <= size_mult * num_commits ||
+			    (max_commits && num_commits > max_commits))) {
+			if (g->odb != ctx->odb)
+				break;
 
-		num_commits += g->num_commits;
-		g = g->base_graph;
+			num_commits += g->num_commits;
+			g = g->base_graph;
 
-		ctx->num_commit_graphs_after--;
+			ctx->num_commit_graphs_after--;
+		}
 	}
 
-	ctx->new_base_graph = g;
+	if (flags != COMMIT_GRAPH_SPLIT_REPLACE)
+		ctx->new_base_graph = g;
+	else if (ctx->num_commit_graphs_after != 1)
+		BUG("split_graph_merge_strategy: num_commit_graphs_after "
+		    "should be 1 with --split=replace");
 
 	if (ctx->num_commit_graphs_after == 2) {
 		char *old_graph_name = get_commit_graph_filename(g->odb);
@@ -1570,8 +1873,8 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 		free(old_graph_name);
 	}
 
-	ALLOC_ARRAY(ctx->commit_graph_filenames_after, ctx->num_commit_graphs_after);
-	ALLOC_ARRAY(ctx->commit_graph_hash_after, ctx->num_commit_graphs_after);
+	CALLOC_ARRAY(ctx->commit_graph_filenames_after, ctx->num_commit_graphs_after);
+	CALLOC_ARRAY(ctx->commit_graph_hash_after, ctx->num_commit_graphs_after);
 
 	for (i = 0; i < ctx->num_commit_graphs_after &&
 		    i < ctx->num_commit_graphs_before; i++)
@@ -1707,7 +2010,7 @@ static void expire_commit_graphs(struct write_commit_graph_context *ctx)
 	timestamp_t expire_time = time(NULL);
 
 	if (ctx->split_opts && ctx->split_opts->expire_time)
-		expire_time -= ctx->split_opts->expire_time;
+		expire_time = ctx->split_opts->expire_time;
 	if (!ctx->split) {
 		char *chain_file_name = get_chain_filename(ctx->odb);
 		unlink(chain_file_name);
@@ -1756,13 +2059,14 @@ out:
 
 int write_commit_graph(struct object_directory *odb,
 		       struct string_list *pack_indexes,
-		       struct string_list *commit_hex,
+		       struct oidset *commits,
 		       enum commit_graph_write_flags flags,
 		       const struct split_commit_graph_opts *split_opts)
 {
 	struct write_commit_graph_context *ctx;
 	uint32_t i, count_distinct = 0;
 	int res = 0;
+	int replace = 0;
 
 	if (!commit_graph_compatible(the_repository))
 		return 0;
@@ -1773,8 +2077,9 @@ 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 (ctx->split) {
 		struct commit_graph *g;
@@ -1797,6 +2102,9 @@ int write_commit_graph(struct object_directory *odb,
 				g = g->base_graph;
 			}
 		}
+
+		if (ctx->split_opts)
+			replace = ctx->split_opts->flags & COMMIT_GRAPH_SPLIT_REPLACE;
 	}
 
 	ctx->approx_nr_objects = approximate_object_count();
@@ -1824,17 +2132,20 @@ int write_commit_graph(struct object_directory *odb,
 	}
 
 	if (pack_indexes) {
+		ctx->order_by_pack = 1;
 		if ((res = fill_oids_from_packs(ctx, pack_indexes)))
 			goto cleanup;
 	}
 
-	if (commit_hex) {
-		if ((res = fill_oids_from_commit_hex(ctx, commit_hex)))
+	if (commits) {
+		if ((res = fill_oids_from_commits(ctx, commits)))
 			goto cleanup;
 	}
 
-	if (!pack_indexes && !commit_hex)
+	if (!pack_indexes && !commits) {
+		ctx->order_by_pack = 1;
 		fill_oids_from_all_packs(ctx);
+	}
 
 	close_reachable(ctx);
 
@@ -1857,18 +2168,22 @@ int write_commit_graph(struct object_directory *odb,
 		goto cleanup;
 	}
 
-	if (!ctx->commits.nr)
+	if (!ctx->commits.nr && !replace)
 		goto cleanup;
 
 	if (ctx->split) {
 		split_graph_merge_strategy(ctx);
 
-		merge_commit_graphs(ctx);
+		if (!replace)
+			merge_commit_graphs(ctx);
 	} else
 		ctx->num_commit_graphs_after = 1;
 
 	compute_generation_numbers(ctx);
 
+	if (ctx->changed_paths)
+		compute_bloom_filters(ctx);
+
 	res = write_commit_graph_file(ctx);
 
 	if (ctx->split)
@@ -1993,6 +2308,7 @@ 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);
@@ -2031,8 +2347,9 @@ 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;
@@ -2042,7 +2359,7 @@ 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));
@@ -2062,10 +2379,11 @@ 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)
@@ -2088,12 +2406,12 @@ void free_commit_graph(struct commit_graph *g)
 {
 	if (!g)
 		return;
-	if (g->graph_fd >= 0) {
+	if (g->data) {
 		munmap((void *)g->data, g->data_len);
 		g->data = NULL;
-		close(g->graph_fd);
 	}
 	free(g->filename);
+	free(g->bloom_filter_settings);
 	free(g);
 }