patch, 10 partsmore miscellaneous Bloom filter improvements

blame.c, bloom.c, commit-graph.c, commit-graph.h, revision.c, t/t4216-log-bloom.sh, t/t5324-split-commit-graph.sh

diff --git a/blame.c b/blame.c
index 82fa16d658..3e5f8787bc 100644
--- a/blame.c
+++ b/blame.c
@@ -2891,16 +2891,18 @@ void setup_blame_bloom_data(struct blame_scoreboard *sb,
 			    const char *path)
 {
 	struct blame_bloom_data *bd;
+	struct bloom_filter_settings *bs;
 
 	if (!sb->repo->objects->commit_graph)
 		return;
 
-	if (!sb->repo->objects->commit_graph->bloom_filter_settings)
+	bs = get_bloom_filter_settings(sb->repo);
+	if (!bs)
 		return;
 
 	bd = xmalloc(sizeof(struct blame_bloom_data));
 
-	bd->settings = sb->repo->objects->commit_graph->bloom_filter_settings;
+	bd->settings = bs;
 
 	bd->alloc = 4;
 	bd->nr = 0;
diff --git a/bloom.c b/bloom.c
index 1a573226e7..cd9380ac62 100644
--- a/bloom.c
+++ b/bloom.c
@@ -38,7 +38,7 @@ static int load_bloom_filter_from_graph(struct commit_graph *g,
 	while (graph_pos < g->num_commits_in_base)
 		g = g->base_graph;
 
-	/* The commit graph commit 'c' lives in doesn't carry bloom filters. */
+	/* The commit graph commit 'c' lives in doesn't carry Bloom filters. */
 	if (!g->chunk_bloom_indexes)
 		return 0;
 
@@ -195,8 +195,8 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 	if (!filter->data) {
 		load_commit_graph_info(r, c);
 		if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH &&
-			r->objects->commit_graph->chunk_bloom_indexes)
-			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c);
+			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c))
+				return filter;
 	}
 
 	if (filter->data)
diff --git a/commit-graph.c b/commit-graph.c
index e51c91dd5b..d4b06811be 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -660,6 +660,17 @@ int generation_numbers_enabled(struct repository *r)
 	return !!first_generation;
 }
 
+struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r)
+{
+	struct commit_graph *g = r->objects->commit_graph;
+	while (g) {
+		if (g->bloom_filter_settings)
+			return g->bloom_filter_settings;
+		g = g->base_graph;
+	}
+	return NULL;
+}
+
 static void close_commit_graph_one(struct commit_graph *g)
 {
 	if (!g)
diff --git a/commit-graph.h b/commit-graph.h
index 09a97030dc..0677dd1031 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -87,6 +87,8 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size);
  */
 int generation_numbers_enabled(struct repository *r);
 
+struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r);
+
 enum commit_graph_write_flags {
 	COMMIT_GRAPH_WRITE_APPEND     = (1 << 0),
 	COMMIT_GRAPH_WRITE_PROGRESS   = (1 << 1),
diff --git a/revision.c b/revision.c
index 6de29cdf7a..e244beed05 100644
--- a/revision.c
+++ b/revision.c
@@ -684,7 +684,7 @@ static void prepare_to_use_bloom_filter(struct rev_info *revs)
 	if (!revs->repo->objects->commit_graph)
 		return;
 
-	revs->bloom_filter_settings = revs->repo->objects->commit_graph->bloom_filter_settings;
+	revs->bloom_filter_settings = get_bloom_filter_settings(revs->repo);
 	if (!revs->bloom_filter_settings)
 		return;
 
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index c21cc160f3..c9f9bdf1ba 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -60,7 +60,7 @@ setup () {
 
 test_bloom_filters_used () {
 	log_args=$1
-	bloom_trace_prefix="statistics:{\"filter_not_present\":0,\"maybe\""
+	bloom_trace_prefix="statistics:{\"filter_not_present\":${2:-0},\"maybe\""
 	setup "$log_args" &&
 	grep -q "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.perf" &&
 	test_cmp log_wo_bloom log_w_bloom &&
@@ -134,8 +134,11 @@ test_expect_success 'setup - add commit-graph to the chain without Bloom filters
 	test_line_count = 2 .git/objects/info/commit-graphs/commit-graph-chain
 '
 
-test_expect_success 'Do not use Bloom filters if the latest graph does not have Bloom filters.' '
-	test_bloom_filters_not_used "-- A/B"
+test_expect_success 'use Bloom filters even if the latest graph does not have Bloom filters' '
+	# Ensure that the number of empty filters is equal to the number of
+	# filters in the latest graph layer to prove that they are loaded (and
+	# ignored).
+	test_bloom_filters_used "-- A/B" 3
 '
 
 test_expect_success 'setup - add commit-graph to the chain with Bloom filters' '
diff --git a/t/t5324-split-commit-graph.sh b/t/t5324-split-commit-graph.sh
index 9b850ea907..5bdfd53ef9 100755
--- a/t/t5324-split-commit-graph.sh
+++ b/t/t5324-split-commit-graph.sh
@@ -425,4 +425,17 @@ done <<\EOF
 0600 -r--------
 EOF
 
+test_expect_success '--split=replace with partial Bloom data' '
+	rm -rf $graphdir $infodir/commit-graph &&
+	git reset --hard commits/3 &&
+	git rev-list -1 HEAD~2 >a &&
+	git rev-list -1 HEAD~1 >b &&
+	git commit-graph write --split=no-merge --stdin-commits --changed-paths <a &&
+	git commit-graph write --split=no-merge --stdin-commits <b &&
+	git commit-graph write --split=replace --stdin-commits --changed-paths <c &&
+	ls $graphdir/graph-*.graph >graph-files &&
+	test_line_count = 1 graph-files &&
+	verify_chain_files_exist $graphdir
+'
+
 test_done

builtin/commit-graph.c, commit-graph.c, commit-graph.h, fuzz-commit-graph.c

diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index 523501f217..ba5584463f 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -106,7 +106,7 @@ static int graph_verify(int argc, const char **argv)
 	FREE_AND_NULL(graph_name);
 
 	if (open_ok)
-		graph = load_commit_graph_one_fd_st(fd, &st, odb);
+		graph = load_commit_graph_one_fd_st(the_repository, fd, &st, odb);
 	else
 		graph = read_commit_graph_one(the_repository, odb);
 
diff --git a/commit-graph.c b/commit-graph.c
index d4b06811be..81a6f2a8ce 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -224,7 +224,8 @@ int open_commit_graph(const char *graph_file, int *fd, struct stat *st)
 	return 1;
 }
 
-struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st,
+struct commit_graph *load_commit_graph_one_fd_st(struct repository *r,
+						 int fd, struct stat *st,
 						 struct object_directory *odb)
 {
 	void *graph_map;
@@ -240,7 +241,7 @@ struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st,
 	}
 	graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0);
 	close(fd);
-	ret = parse_commit_graph(graph_map, graph_size);
+	ret = parse_commit_graph(r, graph_map, graph_size);
 
 	if (ret)
 		ret->odb = odb;
@@ -280,7 +281,8 @@ static int verify_commit_graph_lite(struct commit_graph *g)
 	return 0;
 }
 
-struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
+struct commit_graph *parse_commit_graph(struct repository *r,
+					void *graph_map, size_t graph_size)
 {
 	const unsigned char *data, *chunk_lookup;
 	uint32_t i;
@@ -445,7 +447,9 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
 	return NULL;
 }
 
-static struct commit_graph *load_commit_graph_one(const char *graph_file,
+
+static struct commit_graph *load_commit_graph_one(struct repository *r,
+						  const char *graph_file,
 						  struct object_directory *odb)
 {
 
@@ -457,7 +461,7 @@ static struct commit_graph *load_commit_graph_one(const char *graph_file,
 	if (!open_ok)
 		return NULL;
 
-	g = load_commit_graph_one_fd_st(fd, &st, odb);
+	g = load_commit_graph_one_fd_st(r, fd, &st, odb);
 
 	if (g)
 		g->filename = xstrdup(graph_file);
@@ -469,7 +473,7 @@ static struct commit_graph *load_commit_graph_v1(struct repository *r,
 						 struct object_directory *odb)
 {
 	char *graph_name = get_commit_graph_filename(odb);
-	struct commit_graph *g = load_commit_graph_one(graph_name, odb);
+	struct commit_graph *g = load_commit_graph_one(r, graph_name, odb);
 	free(graph_name);
 
 	return g;
@@ -550,7 +554,7 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r,
 		valid = 0;
 		for (odb = r->objects->odb; odb; odb = odb->next) {
 			char *graph_name = get_split_graph_filename(odb, line.buf);
-			struct commit_graph *g = load_commit_graph_one(graph_name, odb);
+			struct commit_graph *g = load_commit_graph_one(r, graph_name, odb);
 
 			free(graph_name);
 
diff --git a/commit-graph.h b/commit-graph.h
index 0677dd1031..d9acb22bac 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -75,11 +75,13 @@ struct commit_graph {
 	struct bloom_filter_settings *bloom_filter_settings;
 };
 
-struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st,
+struct commit_graph *load_commit_graph_one_fd_st(struct repository *r,
+						 int fd, struct stat *st,
 						 struct object_directory *odb);
 struct commit_graph *read_commit_graph_one(struct repository *r,
 					   struct object_directory *odb);
-struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size);
+struct commit_graph *parse_commit_graph(struct repository *r,
+					void *graph_map, size_t graph_size);
 
 /*
  * Return 1 if and only if the repository has a commit-graph
diff --git a/fuzz-commit-graph.c b/fuzz-commit-graph.c
index 430817214d..e7cf6d5b0f 100644
--- a/fuzz-commit-graph.c
+++ b/fuzz-commit-graph.c
@@ -1,7 +1,8 @@
 #include "commit-graph.h"
 #include "repository.h"
 
-struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size);
+struct commit_graph *parse_commit_graph(struct repository *r,
+					void *graph_map, size_t graph_size);
 
 int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size);
 
@@ -10,7 +11,7 @@ int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size)
 	struct commit_graph *g;
 
 	initialize_the_repository();
-	g = parse_commit_graph((void *)data, size);
+	g = parse_commit_graph(the_repository, (void *)data, size);
 	repo_clear(the_repository);
 	free_commit_graph(g);
 

diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index c9f9bdf1ba..fe19f6a60c 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -53,7 +53,7 @@ sane_unset GIT_TRACE2_PERF_BRIEF
 sane_unset GIT_TRACE2_CONFIG_PARAMS
 
 setup () {
-	rm "$TRASH_DIRECTORY/trace.perf"
+	rm -f "$TRASH_DIRECTORY/trace.perf" &&
 	git -c core.commitGraph=false log --pretty="format:%s" $1 >log_wo_bloom &&
 	GIT_TRACE2_PERF="$TRASH_DIRECTORY/trace.perf" git -c core.commitGraph=true log --pretty="format:%s" $1 >log_w_bloom
 }

diff --git a/t/helper/test-read-graph.c b/t/helper/test-read-graph.c
index 6d0c962438..5f585a1725 100644
--- a/t/helper/test-read-graph.c
+++ b/t/helper/test-read-graph.c
@@ -12,11 +12,12 @@ int cmd__read_graph(int argc, const char **argv)
 	setup_git_directory();
 	odb = the_repository->objects->odb;
 
+	prepare_repo_settings(the_repository);
+
 	graph = read_commit_graph_one(the_repository, odb);
 	if (!graph)
 		return 1;
 
-
 	printf("header: %08x %d %d %d %d\n",
 		ntohl(*(uint32_t*)graph->data),
 		*(unsigned char*)(graph->data + 4),

Documentation/config.txt, Documentation/config/commitgraph.txt, commit-graph.c, repo-settings.c, repository.h, t/t4216-log-bloom.sh

diff --git a/Documentation/config.txt b/Documentation/config.txt
index ef0768b91a..78883c6e63 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -340,6 +340,8 @@ include::config/column.txt[]
 
 include::config/commit.txt[]
 
+include::config/commitgraph.txt[]
+
 include::config/credential.txt[]
 
 include::config/completion.txt[]
diff --git a/Documentation/config/commitgraph.txt b/Documentation/config/commitgraph.txt
new file mode 100644
index 0000000000..bb78e72f1b
--- /dev/null
+++ b/Documentation/config/commitgraph.txt
@@ -0,0 +1,4 @@
+commitgraph.readChangedPaths::
+	If true, then git will use the changed-path Bloom filters in the
+	commit-graph file (if it exists, and they are present). Defaults to
+	true. See linkgit:git-commit-graph[1] for more information.
diff --git a/commit-graph.c b/commit-graph.c
index 81a6f2a8ce..cb9d7fea04 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -320,6 +320,8 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 		return NULL;
 	}
 
+	prepare_repo_settings(r);
+
 	graph = alloc_commit_graph();
 
 	graph->hash_len = the_hash_algo->rawsz;
@@ -396,14 +398,14 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 		case GRAPH_CHUNKID_BLOOMINDEXES:
 			if (graph->chunk_bloom_indexes)
 				chunk_repeated = 1;
-			else
+			else if (r->settings.commit_graph_read_changed_paths)
 				graph->chunk_bloom_indexes = data + chunk_offset;
 			break;
 
 		case GRAPH_CHUNKID_BLOOMDATA:
 			if (graph->chunk_bloom_data)
 				chunk_repeated = 1;
-			else {
+			else if (r->settings.commit_graph_read_changed_paths) {
 				uint32_t hash_version;
 				graph->chunk_bloom_data = data + chunk_offset;
 				hash_version = get_be32(data + chunk_offset);
diff --git a/repo-settings.c b/repo-settings.c
index 0918408b34..9e551bc03d 100644
--- a/repo-settings.c
+++ b/repo-settings.c
@@ -17,9 +17,12 @@ void prepare_repo_settings(struct repository *r)
 
 	if (!repo_config_get_bool(r, "core.commitgraph", &value))
 		r->settings.core_commit_graph = value;
+	if (!repo_config_get_bool(r, "commitgraph.readchangedpaths", &value))
+		r->settings.commit_graph_read_changed_paths = value;
 	if (!repo_config_get_bool(r, "gc.writecommitgraph", &value))
 		r->settings.gc_write_commit_graph = value;
 	UPDATE_DEFAULT_BOOL(r->settings.core_commit_graph, 1);
+	UPDATE_DEFAULT_BOOL(r->settings.commit_graph_read_changed_paths, 1);
 	UPDATE_DEFAULT_BOOL(r->settings.gc_write_commit_graph, 1);
 
 	if (!repo_config_get_int(r, "index.version", &value))
diff --git a/repository.h b/repository.h
index 3c1f7d54bd..81759b7d27 100644
--- a/repository.h
+++ b/repository.h
@@ -29,6 +29,7 @@ struct repo_settings {
 	int initialized;
 
 	int core_commit_graph;
+	int commit_graph_read_changed_paths;
 	int gc_write_commit_graph;
 	int fetch_write_commit_graph;
 
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index fe19f6a60c..b3d1f596f8 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -90,7 +90,9 @@ do
 		      "--ancestry-path side..master"
 	do
 		test_expect_success "git log option: $option for path: $path" '
-			test_bloom_filters_used "$option -- $path"
+			test_bloom_filters_used "$option -- $path" &&
+			test_config commitgraph.readChangedPaths false &&
+			test_bloom_filters_not_used "$option -- $path"
 		'
 	done
 done

diff --git a/commit-graph.c b/commit-graph.c
index cb9d7fea04..d6ea556649 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -79,10 +79,18 @@ static void set_commit_pos(struct repository *r, const struct object_id *oid)
 	*commit_pos_at(&commit_pos, commit) = max_pos++;
 }
 
-static int commit_pos_cmp(const void *va, const void *vb)
+struct packed_commit_list {
+	struct commit **list;
+	int nr;
+	int alloc;
+};
+
+static int commit_pos_cmp(const void *va, const void *vb, void *ctx)
 {
-	const struct commit *a = *(const struct commit **)va;
-	const struct commit *b = *(const struct commit **)vb;
+	struct packed_commit_list *commits = ctx;
+
+	const struct commit *a = commits->list[*(int *)va];
+	const struct commit *b = commits->list[*(int *)vb];
 	return commit_pos_at(&commit_pos, a) -
 	       commit_pos_at(&commit_pos, b);
 }
@@ -139,10 +147,12 @@ static struct commit_graph_data *commit_graph_data_at(const struct commit *c)
 	return data;
 }
 
-static int commit_gen_cmp(const void *va, const void *vb)
+static int commit_gen_cmp(const void *va, const void *vb, void *ctx)
 {
-	const struct commit *a = *(const struct commit **)va;
-	const struct commit *b = *(const struct commit **)vb;
+	struct packed_commit_list *commits = ctx;
+
+	const struct commit *a = commits->list[*(int *)va];
+	const struct commit *b = commits->list[*(int *)vb];
 
 	uint32_t generation_a = commit_graph_generation(a);
 	uint32_t generation_b = commit_graph_generation(b);
@@ -923,12 +933,6 @@ struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit
 	return get_commit_tree_in_graph_one(r, r->objects->commit_graph, c);
 }
 
-struct packed_commit_list {
-	struct commit **list;
-	int nr;
-	int alloc;
-};
-
 struct packed_oid_list {
 	struct object_id *list;
 	int nr;
@@ -1389,7 +1393,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 {
 	int i;
 	struct progress *progress = NULL;
-	struct commit **sorted_commits;
+	int *sorted_commits;
 
 	init_bloom_filters();
 
@@ -1399,15 +1403,15 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 			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++)
+		sorted_commits[i] = i;
+	QSORT_S(sorted_commits, ctx->commits.nr,
+		ctx->order_by_pack ? commit_pos_cmp : commit_gen_cmp,
+		&ctx->commits);
 
 	for (i = 0; i < ctx->commits.nr; i++) {
-		struct commit *c = sorted_commits[i];
+		int pos = sorted_commits[i];
+		struct commit *c = ctx->commits.list[pos];
 		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);

Documentation/technical/commit-graph-format.txt, commit-graph.c, commit-graph.h, t/t4216-log-bloom.sh

diff --git a/Documentation/technical/commit-graph-format.txt b/Documentation/technical/commit-graph-format.txt
index 440541045d..a7191c03d3 100644
--- a/Documentation/technical/commit-graph-format.txt
+++ b/Documentation/technical/commit-graph-format.txt
@@ -123,6 +123,15 @@ CHUNK DATA:
       of length zero.
     * The BDAT chunk is present if and only if BIDX is present.
 
+  Large Bloom Filters (ID: {'B', 'F', 'X', 'L'}) [Optional]
+    * It contains a list of 'eword_t's (the length of this list is determined by
+      the width of the chunk) which is a bitmap. The 'i'th bit is set exactly
+      when the 'i'th commit in the graph has a changed-path Bloom filter with
+      zero entries (either because the commit is empty, or because it contains
+      more than 512 changed paths).
+    * The BFXL chunk is present on newer versions of Git iff the BIDX and BDAT
+      chunks are also present.
+
   Base Graphs List (ID: {'B', 'A', 'S', 'E'}) [Optional]
       This list of H-byte hashes describe a set of B commit-graph files that
       form a commit-graph chain. The graph position for the ith commit in this
diff --git a/commit-graph.c b/commit-graph.c
index d6ea556649..c870ffe0ed 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -41,8 +41,9 @@ void git_test_write_commit_graph_or_die(void)
 #define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
 #define GRAPH_CHUNKID_BLOOMINDEXES 0x42494458 /* "BIDX" */
 #define GRAPH_CHUNKID_BLOOMDATA 0x42444154 /* "BDAT" */
+#define GRAPH_CHUNKID_BLOOMLARGE 0x4246584c /* "BFXL" */
 #define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */
-#define MAX_NUM_CHUNKS 7
+#define MAX_NUM_CHUNKS 8
 
 #define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
 
@@ -429,6 +430,17 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 				graph->bloom_filter_settings->bits_per_entry = get_be32(data + chunk_offset + 8);
 			}
 			break;
+
+		case GRAPH_CHUNKID_BLOOMLARGE:
+			if (graph->bloom_large.word_alloc)
+				chunk_repeated = 1;
+			else if (r->settings.commit_graph_read_changed_paths) {
+				uint32_t alloc = get_be64(chunk_lookup + 4) - chunk_offset;
+
+				graph->bloom_large.word_alloc = alloc;
+				graph->bloom_large.words = (eword_t *)(data + chunk_offset);
+			}
+			break;
 		}
 
 		if (chunk_repeated) {
@@ -443,6 +455,8 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 		/* We need both the bloom chunks to exist together. Else ignore the data */
 		graph->chunk_bloom_indexes = NULL;
 		graph->chunk_bloom_data = NULL;
+		graph->bloom_large.words = NULL;
+		graph->bloom_large.word_alloc = 0;
 		FREE_AND_NULL(graph->bloom_filter_settings);
 	}
 
@@ -933,6 +947,21 @@ struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit
 	return get_commit_tree_in_graph_one(r, r->objects->commit_graph, c);
 }
 
+static int get_bloom_filter_large_in_graph(struct commit_graph *g,
+					   const struct commit *c)
+{
+	uint32_t graph_pos = commit_graph_position(c);
+	if (graph_pos == COMMIT_NOT_FROM_GRAPH)
+		return 0;
+
+	while (g && graph_pos < g->num_commits_in_base)
+		g = g->base_graph;
+
+	if (!(g && g->bloom_large.word_alloc))
+		return 0;
+	return bitmap_get(&g->bloom_large, graph_pos - g->num_commits_in_base);
+}
+
 struct packed_oid_list {
 	struct object_id *list;
 	int nr;
@@ -969,6 +998,11 @@ struct write_commit_graph_context {
 	const struct split_commit_graph_opts *split_opts;
 	size_t total_bloom_filter_data_size;
 	const struct bloom_filter_settings *bloom_settings;
+	struct bitmap *bloom_large;
+
+	int count_bloom_filter_known_large;
+	int count_bloom_filter_found_large;
+	int count_bloom_filter_computed;
 };
 
 static int write_graph_chunk_fanout(struct hashfile *f,
@@ -1231,6 +1265,15 @@ static int write_graph_chunk_bloom_data(struct hashfile *f,
 	return 0;
 }
 
+static int write_graph_chunk_bloom_large(struct hashfile *f,
+					  struct write_commit_graph_context *ctx)
+{
+	trace2_region_enter("commit-graph", "bloom_large", ctx->r);
+	hashwrite(f, ctx->bloom_large->words, ctx->bloom_large->word_alloc * sizeof(eword_t));
+	trace2_region_leave("commit-graph", "bloom_large", ctx->r);
+	return 0;
+}
+
 static int oid_compare(const void *_a, const void *_b)
 {
 	const struct object_id *a = (const struct object_id *)_a;
@@ -1389,6 +1432,24 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 	stop_progress(&ctx->progress);
 }
 
+static void trace2_bloom_filter_write_statistics(struct write_commit_graph_context *ctx)
+{
+	struct json_writer jw = JSON_WRITER_INIT;
+
+	jw_object_begin(&jw, 0);
+	jw_object_intmax(&jw, "filter_known_large",
+			 ctx->count_bloom_filter_known_large);
+	jw_object_intmax(&jw, "filter_found_large",
+			 ctx->count_bloom_filter_found_large);
+	jw_object_intmax(&jw, "filter_computed",
+			 ctx->count_bloom_filter_computed);
+	jw_end(&jw);
+
+	trace2_data_json("commit-graph", the_repository, "bloom_statistics", &jw);
+
+	jw_release(&jw);
+}
+
 static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 {
 	int i;
@@ -1396,6 +1457,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 	int *sorted_commits;
 
 	init_bloom_filters();
+	ctx->bloom_large = bitmap_word_alloc(ctx->commits.nr / BITS_IN_EWORD);
 
 	if (ctx->report_progress)
 		progress = start_delayed_progress(
@@ -1412,11 +1474,24 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 	for (i = 0; i < ctx->commits.nr; i++) {
 		int pos = sorted_commits[i];
 		struct commit *c = ctx->commits.list[pos];
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, c, 1);
-		ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
+		if (get_bloom_filter_large_in_graph(ctx->r->objects->commit_graph, c)) {
+			bitmap_set(ctx->bloom_large, pos);
+			ctx->count_bloom_filter_known_large++;
+		} else {
+			struct bloom_filter *filter = get_bloom_filter(ctx->r, c, 1);
+			if (!filter->len) {
+				bitmap_set(ctx->bloom_large, pos);
+				ctx->count_bloom_filter_found_large++;
+			}
+			ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
+			ctx->count_bloom_filter_computed++;
+		}
 		display_progress(progress, i + 1);
 	}
 
+	if (trace2_is_enabled())
+		trace2_bloom_filter_write_statistics(ctx);
+
 	free(sorted_commits);
 	stop_progress(&progress);
 }
@@ -1739,6 +1814,10 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 					  + ctx->total_bloom_filter_data_size;
 		chunks[num_chunks].write_fn = write_graph_chunk_bloom_data;
 		num_chunks++;
+		chunks[num_chunks].id = GRAPH_CHUNKID_BLOOMLARGE;
+		chunks[num_chunks].size = sizeof(eword_t) * ctx->bloom_large->word_alloc;
+		chunks[num_chunks].write_fn = write_graph_chunk_bloom_large;
+		num_chunks++;
 	}
 	if (ctx->num_commit_graphs_after > 1) {
 		chunks[num_chunks].id = GRAPH_CHUNKID_BASE;
diff --git a/commit-graph.h b/commit-graph.h
index d9acb22bac..afbc5fa41e 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -4,6 +4,7 @@
 #include "git-compat-util.h"
 #include "object-store.h"
 #include "oidset.h"
+#include "ewah/ewok.h"
 
 #define GIT_TEST_COMMIT_GRAPH "GIT_TEST_COMMIT_GRAPH"
 #define GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE "GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE"
@@ -71,6 +72,7 @@ struct commit_graph {
 	const unsigned char *chunk_base_graphs;
 	const unsigned char *chunk_bloom_indexes;
 	const unsigned char *chunk_bloom_data;
+	struct bitmap bloom_large;
 
 	struct bloom_filter_settings *bloom_filter_settings;
 };
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index b3d1f596f8..231dc8a3a7 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -33,7 +33,7 @@ test_expect_success 'setup test - repo, commits, commit graph, log outputs' '
 	git commit-graph write --reachable --changed-paths
 '
 graph_read_expect () {
-	NUM_CHUNKS=5
+	NUM_CHUNKS=6
 	cat >expect <<- EOF
 	header: 43475048 1 1 $NUM_CHUNKS 0
 	num_commits: $1
@@ -195,5 +195,23 @@ test_expect_success 'correctly report changes over limit' '
 		done
 	)
 '
+test_bloom_filters_computed () {
+	commit_graph_args=$1
+	bloom_trace_prefix="{\"filter_known_large\":$2,\"filter_found_large\":$3,\"filter_computed\":$4"
+	rm -f "$TRASH_DIRECTORY/trace.event" &&
+	GIT_TRACE2_EVENT="$TRASH_DIRECTORY/trace.event" git commit-graph write $commit_graph_args &&
+	grep "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.event"
+}
+
+test_expect_success 'Bloom generation does not recompute too-large filters' '
+	(
+		cd 513changes &&
+		git commit-graph write --reachable --changed-paths \
+			--split=replace &&
+		test_commit c1 filter &&
+		test_bloom_filters_computed "--reachable --changed-paths --split=replace" \
+			1 0 1
+	)
+'
 
 test_done

blame.c, bloom.c, bloom.h, commit-graph.c, line-log.c, revision.c, t/helper/test-bloom.c

diff --git a/blame.c b/blame.c
index 3e5f8787bc..756285fca7 100644
--- a/blame.c
+++ b/blame.c
@@ -1275,7 +1275,7 @@ static int maybe_changed_path(struct repository *r,
 	if (commit_graph_generation(origin->commit) == GENERATION_NUMBER_INFINITY)
 		return 1;
 
-	filter = get_bloom_filter(r, origin->commit, 0);
+	filter = get_bloom_filter(r, origin->commit);
 
 	if (!filter)
 		return 1;
diff --git a/bloom.c b/bloom.c
index cd9380ac62..a8a21762f4 100644
--- a/bloom.c
+++ b/bloom.c
@@ -177,9 +177,10 @@ static int pathmap_cmp(const void *hashmap_cmp_fn_data,
 	return strcmp(e1->path, e2->path);
 }
 
-struct bloom_filter *get_bloom_filter(struct repository *r,
-				      struct commit *c,
-				      int compute_if_not_present)
+struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
+						 struct commit *c,
+						 int compute_if_not_present,
+						 int *computed)
 {
 	struct bloom_filter *filter;
 	struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
@@ -187,6 +188,9 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 	struct diff_options diffopt;
 	int max_changes = 512;
 
+	if (computed)
+		*computed = 0;
+
 	if (!bloom_filters.slab_size)
 		return NULL;
 
@@ -273,6 +277,9 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 		filter->len = 0;
 	}
 
+	if (computed)
+		*computed = 1;
+
 	free(diff_queued_diff.queue);
 	DIFF_QUEUE_CLEAR(&diff_queued_diff);
 
diff --git a/bloom.h b/bloom.h
index d8fbb0fbf1..2fdc2918f8 100644
--- a/bloom.h
+++ b/bloom.h
@@ -80,9 +80,12 @@ void add_key_to_filter(const struct bloom_key *key,
 
 void init_bloom_filters(void);
 
-struct bloom_filter *get_bloom_filter(struct repository *r,
-				      struct commit *c,
-				      int compute_if_not_present);
+struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
+						 struct commit *c,
+						 int compute_if_not_present,
+						 int *computed);
+
+#define get_bloom_filter(r, c) get_or_compute_bloom_filter((r), (c), 0, NULL)
 
 int bloom_filter_contains(const struct bloom_filter *filter,
 			  const struct bloom_key *key,
diff --git a/commit-graph.c b/commit-graph.c
index c870ffe0ed..2e765b26d5 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1214,7 +1214,7 @@ static int write_graph_chunk_bloom_indexes(struct hashfile *f,
 	uint32_t cur_pos = 0;
 
 	while (list < last) {
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list);
 		size_t len = filter ? filter->len : 0;
 		cur_pos += len;
 		display_progress(ctx->progress, ++ctx->progress_cnt);
@@ -1253,7 +1253,7 @@ static int write_graph_chunk_bloom_data(struct hashfile *f,
 	hashwrite_be32(f, ctx->bloom_settings->bits_per_entry);
 
 	while (list < last) {
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list);
 		size_t len = filter ? filter->len : 0;
 
 		display_progress(ctx->progress, ++ctx->progress_cnt);
@@ -1478,7 +1478,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 			bitmap_set(ctx->bloom_large, pos);
 			ctx->count_bloom_filter_known_large++;
 		} else {
-			struct bloom_filter *filter = get_bloom_filter(ctx->r, c, 1);
+			struct bloom_filter *filter = get_or_compute_bloom_filter(ctx->r, c, 1, NULL);
 			if (!filter->len) {
 				bitmap_set(ctx->bloom_large, pos);
 				ctx->count_bloom_filter_found_large++;
diff --git a/line-log.c b/line-log.c
index c53692834d..9e58fd185a 100644
--- a/line-log.c
+++ b/line-log.c
@@ -1159,7 +1159,7 @@ static int bloom_filter_check(struct rev_info *rev,
 		return 1;
 
 	if (!rev->bloom_filter_settings ||
-	    !(filter = get_bloom_filter(rev->repo, commit, 0)))
+	    !(filter = get_bloom_filter(rev->repo, commit)))
 		return 1;
 
 	if (!range)
diff --git a/revision.c b/revision.c
index e244beed05..73b59d2134 100644
--- a/revision.c
+++ b/revision.c
@@ -756,7 +756,7 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
 	if (commit_graph_generation(commit) == GENERATION_NUMBER_INFINITY)
 		return -1;
 
-	filter = get_bloom_filter(revs->repo, commit, 0);
+	filter = get_bloom_filter(revs->repo, commit);
 
 	if (!filter) {
 		count_bloom_filter_not_present++;
diff --git a/t/helper/test-bloom.c b/t/helper/test-bloom.c
index f0aa80b98e..76a28a2199 100644
--- a/t/helper/test-bloom.c
+++ b/t/helper/test-bloom.c
@@ -39,7 +39,7 @@ static void get_bloom_filter_for_commit(const struct object_id *commit_oid)
 	struct bloom_filter *filter;
 	setup_git_directory();
 	c = lookup_commit(the_repository, commit_oid);
-	filter = get_bloom_filter(the_repository, c, 1);
+	filter = get_or_compute_bloom_filter(the_repository, c, 1, NULL);
 	print_bloom_filter(filter);
 }
 

builtin/commit-graph.c, commit-graph.c, commit-graph.h

diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index ba5584463f..38f5f57d15 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -119,7 +119,7 @@ static int graph_verify(int argc, const char **argv)
 }
 
 extern int read_replace_refs;
-static struct split_commit_graph_opts split_opts;
+static struct commit_graph_opts write_opts;
 
 static int write_option_parse_split(const struct option *opt, const char *arg,
 				    int unset)
@@ -187,24 +187,24 @@ static int graph_write(int argc, const char **argv)
 		OPT_BOOL(0, "changed-paths", &opts.enable_changed_paths,
 			N_("enable computation for changed paths")),
 		OPT_BOOL(0, "progress", &opts.progress, N_("force progress reporting")),
-		OPT_CALLBACK_F(0, "split", &split_opts.flags, NULL,
+		OPT_CALLBACK_F(0, "split", &write_opts.flags, NULL,
 			N_("allow writing an incremental commit-graph file"),
 			PARSE_OPT_OPTARG | PARSE_OPT_NONEG,
 			write_option_parse_split),
-		OPT_INTEGER(0, "max-commits", &split_opts.max_commits,
+		OPT_INTEGER(0, "max-commits", &write_opts.max_commits,
 			N_("maximum number of commits in a non-base split commit-graph")),
-		OPT_INTEGER(0, "size-multiple", &split_opts.size_multiple,
+		OPT_INTEGER(0, "size-multiple", &write_opts.size_multiple,
 			N_("maximum ratio between two levels of a split commit-graph")),
-		OPT_EXPIRY_DATE(0, "expire-time", &split_opts.expire_time,
+		OPT_EXPIRY_DATE(0, "expire-time", &write_opts.expire_time,
 			N_("only expire files older than a given date-time")),
 		OPT_END(),
 	};
 
 	opts.progress = isatty(2);
 	opts.enable_changed_paths = -1;
-	split_opts.size_multiple = 2;
-	split_opts.max_commits = 0;
-	split_opts.expire_time = 0;
+	write_opts.size_multiple = 2;
+	write_opts.max_commits = 0;
+	write_opts.expire_time = 0;
 
 	trace2_cmd_mode("write");
 
@@ -232,7 +232,7 @@ static int graph_write(int argc, const char **argv)
 	odb = find_odb(the_repository, opts.obj_dir);
 
 	if (opts.reachable) {
-		if (write_commit_graph_reachable(odb, flags, &split_opts))
+		if (write_commit_graph_reachable(odb, flags, &write_opts))
 			return 1;
 		return 0;
 	}
@@ -261,7 +261,7 @@ static int graph_write(int argc, const char **argv)
 			       opts.stdin_packs ? &pack_indexes : NULL,
 			       opts.stdin_commits ? &commits : NULL,
 			       flags,
-			       &split_opts))
+			       &write_opts))
 		result = 1;
 
 cleanup:
diff --git a/commit-graph.c b/commit-graph.c
index 2e765b26d5..8626024faa 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -995,7 +995,7 @@ struct write_commit_graph_context {
 		 changed_paths:1,
 		 order_by_pack:1;
 
-	const struct split_commit_graph_opts *split_opts;
+	const struct commit_graph_opts *opts;
 	size_t total_bloom_filter_data_size;
 	const struct bloom_filter_settings *bloom_settings;
 	struct bitmap *bloom_large;
@@ -1327,8 +1327,8 @@ 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;
+	enum commit_graph_split_flags flags = ctx->opts ?
+		ctx->opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	if (ctx->report_progress)
 		ctx->progress = start_delayed_progress(
@@ -1520,7 +1520,7 @@ static int add_ref_to_set(const char *refname,
 
 int write_commit_graph_reachable(struct object_directory *odb,
 				 enum commit_graph_write_flags flags,
-				 const struct split_commit_graph_opts *split_opts)
+				 const struct commit_graph_opts *opts)
 {
 	struct oidset commits = OIDSET_INIT;
 	struct refs_cb_data data;
@@ -1537,7 +1537,7 @@ int write_commit_graph_reachable(struct object_directory *odb,
 	stop_progress(&data.progress);
 
 	result = write_commit_graph(odb, NULL, &commits,
-				    flags, split_opts);
+				    flags, opts);
 
 	oidset_clear(&commits);
 	return result;
@@ -1652,8 +1652,8 @@ 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;
+	enum commit_graph_split_flags flags = ctx->opts ?
+		ctx->opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	ctx->num_extra_edges = 0;
 	if (ctx->report_progress)
@@ -1951,13 +1951,13 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 	int max_commits = 0;
 	int size_mult = 2;
 
-	if (ctx->split_opts) {
-		max_commits = ctx->split_opts->max_commits;
+	if (ctx->opts) {
+		max_commits = ctx->opts->max_commits;
 
-		if (ctx->split_opts->size_multiple)
-			size_mult = ctx->split_opts->size_multiple;
+		if (ctx->opts->size_multiple)
+			size_mult = ctx->opts->size_multiple;
 
-		flags = ctx->split_opts->flags;
+		flags = ctx->opts->flags;
 	}
 
 	g = ctx->r->objects->commit_graph;
@@ -2135,8 +2135,8 @@ static void expire_commit_graphs(struct write_commit_graph_context *ctx)
 	size_t dirnamelen;
 	timestamp_t expire_time = time(NULL);
 
-	if (ctx->split_opts && ctx->split_opts->expire_time)
-		expire_time = ctx->split_opts->expire_time;
+	if (ctx->opts && ctx->opts->expire_time)
+		expire_time = ctx->opts->expire_time;
 	if (!ctx->split) {
 		char *chain_file_name = get_chain_filename(ctx->odb);
 		unlink(chain_file_name);
@@ -2187,7 +2187,7 @@ int write_commit_graph(struct object_directory *odb,
 		       struct string_list *pack_indexes,
 		       struct oidset *commits,
 		       enum commit_graph_write_flags flags,
-		       const struct split_commit_graph_opts *split_opts)
+		       const struct commit_graph_opts *opts)
 {
 	struct write_commit_graph_context *ctx;
 	uint32_t i, count_distinct = 0;
@@ -2203,7 +2203,7 @@ 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->split_opts = split_opts;
+	ctx->opts = opts;
 	ctx->total_bloom_filter_data_size = 0;
 
 	if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS)
@@ -2243,15 +2243,15 @@ int write_commit_graph(struct object_directory *odb,
 			}
 		}
 
-		if (ctx->split_opts)
-			replace = ctx->split_opts->flags & COMMIT_GRAPH_SPLIT_REPLACE;
+		if (ctx->opts)
+			replace = ctx->opts->flags & COMMIT_GRAPH_SPLIT_REPLACE;
 	}
 
 	ctx->approx_nr_objects = approximate_object_count();
 	ctx->oids.alloc = ctx->approx_nr_objects / 32;
 
-	if (ctx->split && split_opts && ctx->oids.alloc > split_opts->max_commits)
-		ctx->oids.alloc = split_opts->max_commits;
+	if (ctx->split && opts && ctx->oids.alloc > opts->max_commits)
+		ctx->oids.alloc = opts->max_commits;
 
 	if (ctx->append) {
 		prepare_commit_graph_one(ctx->r, ctx->odb);
diff --git a/commit-graph.h b/commit-graph.h
index afbc5fa41e..4cd991cf26 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -107,7 +107,7 @@ enum commit_graph_split_flags {
 	COMMIT_GRAPH_SPLIT_REPLACE          = 2
 };
 
-struct split_commit_graph_opts {
+struct commit_graph_opts {
 	int size_multiple;
 	int max_commits;
 	timestamp_t expire_time;
@@ -122,12 +122,12 @@ struct split_commit_graph_opts {
  */
 int write_commit_graph_reachable(struct object_directory *odb,
 				 enum commit_graph_write_flags flags,
-				 const struct split_commit_graph_opts *split_opts);
+				 const struct commit_graph_opts *opts);
 int write_commit_graph(struct object_directory *odb,
 		       struct string_list *pack_indexes,
 		       struct oidset *commits,
 		       enum commit_graph_write_flags flags,
-		       const struct split_commit_graph_opts *split_opts);
+		       const struct commit_graph_opts *opts);
 
 #define COMMIT_GRAPH_VERIFY_SHALLOW	(1 << 0)
 

Documentation/config/commitgraph.txt, Documentation/git-commit-graph.txt, bloom.c, builtin/commit-graph.c, commit-graph.c, commit-graph.h, t/t4216-log-bloom.sh

diff --git a/Documentation/config/commitgraph.txt b/Documentation/config/commitgraph.txt
index bb78e72f1b..46f48d1aa8 100644
--- a/Documentation/config/commitgraph.txt
+++ b/Documentation/config/commitgraph.txt
@@ -1,3 +1,7 @@
+commitgraph.maxNewFilters::
+	Specifies the default value for the `--max-new-filters` option of `git
+	commit-graph write` (c.f., linkgit:git-commit-graph[1]).
+
 commitgraph.readChangedPaths::
 	If true, then git will use the changed-path Bloom filters in the
 	commit-graph file (if it exists, and they are present). Defaults to
diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt
index 17405c73a9..e8034ff0ac 100644
--- a/Documentation/git-commit-graph.txt
+++ b/Documentation/git-commit-graph.txt
@@ -67,6 +67,10 @@ this option is given, future commit-graph writes will automatically assume
 that this option was intended. Use `--no-changed-paths` to stop storing this
 data.
 +
+With the `--max-new-filters=<n>` option, generate at most `n` new Bloom
+filters (if `--changed-paths` is specified). If `n` is `-1`, no limit is
+enforced. Overrides the `graph.maxNewFilters` configuration.
++
 With the `--split[=<strategy>]` option, write the commit-graph as a
 chain of multiple commit-graph files stored in
 `<dir>/info/commit-graphs`. Commit-graph layers are merged based on the
diff --git a/bloom.c b/bloom.c
index a8a21762f4..1742beac9e 100644
--- a/bloom.c
+++ b/bloom.c
@@ -51,6 +51,21 @@ static int load_bloom_filter_from_graph(struct commit_graph *g,
 	else
 		start_index = 0;
 
+	if ((start_index == end_index) &&
+	    (g->bloom_large.word_alloc && !bitmap_get(&g->bloom_large, lex_pos))) {
+		/*
+		 * If the filter is zero-length, either (1) the filter has no
+		 * changes, (2) the filter has too many changes, or (3) it
+		 * wasn't computed (eg., due to '--max-new-filters').
+		 *
+		 * If either (1) or (2) is the case, the 'large' bit will be set
+		 * for this Bloom filter. If it is unset, then it wasn't
+		 * computed. In that case, return nothing, since we don't have
+		 * that filter in the graph.
+		 */
+		return 0;
+	}
+
 	filter->len = end_index - start_index;
 	filter->data = (unsigned char *)(g->chunk_bloom_data +
 					sizeof(unsigned char) * start_index +
diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index 38f5f57d15..aaf54a76db 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -13,7 +13,8 @@ static char const * const builtin_commit_graph_usage[] = {
 	N_("git commit-graph verify [--object-dir <objdir>] [--shallow] [--[no-]progress]"),
 	N_("git commit-graph write [--object-dir <objdir>] [--append] "
 	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
-	   "[--changed-paths] [--[no-]progress] <split options>"),
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
@@ -25,7 +26,8 @@ static const char * const builtin_commit_graph_verify_usage[] = {
 static const char * const builtin_commit_graph_write_usage[] = {
 	N_("git commit-graph write [--object-dir <objdir>] [--append] "
 	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
-	   "[--changed-paths] [--[no-]progress] <split options>"),
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
@@ -162,6 +164,23 @@ static int read_one_commit(struct oidset *commits, struct progress *progress,
 	return 0;
 }
 
+static int write_option_max_new_filters(const struct option *opt,
+					const char *arg,
+					int unset)
+{
+	int *to = opt->value;
+	if (unset)
+		*to = -1;
+	else {
+		const char *s;
+		*to = strtol(arg, (char **)&s, 10);
+		if (*s)
+			return error(_("%s expects a numerical value"),
+				     optname(opt, opt->flags));
+	}
+	return 0;
+}
+
 static int graph_write(int argc, const char **argv)
 {
 	struct string_list pack_indexes = STRING_LIST_INIT_NODUP;
@@ -197,6 +216,9 @@ static int graph_write(int argc, const char **argv)
 			N_("maximum ratio between two levels of a split commit-graph")),
 		OPT_EXPIRY_DATE(0, "expire-time", &write_opts.expire_time,
 			N_("only expire files older than a given date-time")),
+		OPT_CALLBACK_F(0, "max-new-filters", &write_opts.max_new_filters,
+			NULL, N_("maximum number of Bloom filters to compute"),
+			0, write_option_max_new_filters),
 		OPT_END(),
 	};
 
@@ -205,6 +227,7 @@ static int graph_write(int argc, const char **argv)
 	write_opts.size_multiple = 2;
 	write_opts.max_commits = 0;
 	write_opts.expire_time = 0;
+	write_opts.max_new_filters = -1;
 
 	trace2_cmd_mode("write");
 
@@ -270,6 +293,16 @@ static int graph_write(int argc, const char **argv)
 	return result;
 }
 
+static int git_commit_graph_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "graph.maxnewfilters")) {
+		write_opts.max_new_filters = git_config_int(var, value);
+		return 0;
+	}
+
+	return git_default_config(var, value, cb);
+}
+
 int cmd_commit_graph(int argc, const char **argv, const char *prefix)
 {
 	static struct option builtin_commit_graph_options[] = {
@@ -283,7 +316,7 @@ int cmd_commit_graph(int argc, const char **argv, const char *prefix)
 		usage_with_options(builtin_commit_graph_usage,
 				   builtin_commit_graph_options);
 
-	git_config(git_default_config, NULL);
+	git_config(git_commit_graph_config, &opts);
 	argc = parse_options(argc, argv, prefix,
 			     builtin_commit_graph_options,
 			     builtin_commit_graph_usage,
diff --git a/commit-graph.c b/commit-graph.c
index 8626024faa..87ea0437e2 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1455,6 +1455,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 	int i;
 	struct progress *progress = NULL;
 	int *sorted_commits;
+	int max_new_filters;
 
 	init_bloom_filters();
 	ctx->bloom_large = bitmap_word_alloc(ctx->commits.nr / BITS_IN_EWORD);
@@ -1471,6 +1472,9 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 		ctx->order_by_pack ? commit_pos_cmp : commit_gen_cmp,
 		&ctx->commits);
 
+	max_new_filters = ctx->opts->max_new_filters >= 0 ?
+		ctx->opts->max_new_filters : ctx->commits.nr;
+
 	for (i = 0; i < ctx->commits.nr; i++) {
 		int pos = sorted_commits[i];
 		struct commit *c = ctx->commits.list[pos];
@@ -1478,13 +1482,19 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 			bitmap_set(ctx->bloom_large, pos);
 			ctx->count_bloom_filter_known_large++;
 		} else {
-			struct bloom_filter *filter = get_or_compute_bloom_filter(ctx->r, c, 1, NULL);
-			if (!filter->len) {
-				bitmap_set(ctx->bloom_large, pos);
-				ctx->count_bloom_filter_found_large++;
+			int computed = 0;
+			struct bloom_filter *filter = get_or_compute_bloom_filter(
+				ctx->r, c,
+				ctx->count_bloom_filter_computed < max_new_filters,
+				&computed);
+			if (computed) {
+				ctx->count_bloom_filter_computed++;
+				if (filter && !filter->len) {
+					bitmap_set(ctx->bloom_large, pos);
+					ctx->count_bloom_filter_found_large++;
+				}
 			}
-			ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
-			ctx->count_bloom_filter_computed++;
+			ctx->total_bloom_filter_data_size += sizeof(unsigned char) * (filter ? filter->len : 0);
 		}
 		display_progress(progress, i + 1);
 	}
diff --git a/commit-graph.h b/commit-graph.h
index 4cd991cf26..0842d13744 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -112,6 +112,7 @@ struct commit_graph_opts {
 	int max_commits;
 	timestamp_t expire_time;
 	enum commit_graph_split_flags flags;
+	int max_new_filters;
 };
 
 /*
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index 231dc8a3a7..985bea23b2 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -214,4 +214,23 @@ test_expect_success 'Bloom generation does not recompute too-large filters' '
 	)
 '
 
+test_expect_success 'Bloom generation is limited by --max-new-filters' '
+	(
+		cd 513changes &&
+		test_commit c2 filter &&
+		test_commit c3 filter &&
+		test_commit c4 no-filter &&
+		test_bloom_filters_computed "--reachable --changed-paths --split=replace --max-new-filters=2" \
+			1 0 2
+	)
+'
+
+test_expect_success 'Bloom generation backfills previously-skipped filters' '
+	(
+		cd 513changes &&
+		test_bloom_filters_computed "--reachable --changed-paths --split=replace --max-new-filters=1" \
+			1 0 1
+	)
+'
+
 test_done

blame.c, bloom.c, commit-graph.c, commit-graph.h, revision.c, t/t4216-log-bloom.sh, t/t5324-split-commit-graph.sh

diff --git a/blame.c b/blame.c
index 82fa16d658..3e5f8787bc 100644
--- a/blame.c
+++ b/blame.c
@@ -2891,16 +2891,18 @@ void setup_blame_bloom_data(struct blame_scoreboard *sb,
 			    const char *path)
 {
 	struct blame_bloom_data *bd;
+	struct bloom_filter_settings *bs;
 
 	if (!sb->repo->objects->commit_graph)
 		return;
 
-	if (!sb->repo->objects->commit_graph->bloom_filter_settings)
+	bs = get_bloom_filter_settings(sb->repo);
+	if (!bs)
 		return;
 
 	bd = xmalloc(sizeof(struct blame_bloom_data));
 
-	bd->settings = sb->repo->objects->commit_graph->bloom_filter_settings;
+	bd->settings = bs;
 
 	bd->alloc = 4;
 	bd->nr = 0;
diff --git a/bloom.c b/bloom.c
index 1a573226e7..cd9380ac62 100644
--- a/bloom.c
+++ b/bloom.c
@@ -38,7 +38,7 @@ static int load_bloom_filter_from_graph(struct commit_graph *g,
 	while (graph_pos < g->num_commits_in_base)
 		g = g->base_graph;
 
-	/* The commit graph commit 'c' lives in doesn't carry bloom filters. */
+	/* The commit graph commit 'c' lives in doesn't carry Bloom filters. */
 	if (!g->chunk_bloom_indexes)
 		return 0;
 
@@ -195,8 +195,8 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 	if (!filter->data) {
 		load_commit_graph_info(r, c);
 		if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH &&
-			r->objects->commit_graph->chunk_bloom_indexes)
-			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c);
+			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c))
+				return filter;
 	}
 
 	if (filter->data)
diff --git a/commit-graph.c b/commit-graph.c
index e51c91dd5b..d4b06811be 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -660,6 +660,17 @@ int generation_numbers_enabled(struct repository *r)
 	return !!first_generation;
 }
 
+struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r)
+{
+	struct commit_graph *g = r->objects->commit_graph;
+	while (g) {
+		if (g->bloom_filter_settings)
+			return g->bloom_filter_settings;
+		g = g->base_graph;
+	}
+	return NULL;
+}
+
 static void close_commit_graph_one(struct commit_graph *g)
 {
 	if (!g)
diff --git a/commit-graph.h b/commit-graph.h
index 09a97030dc..0677dd1031 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -87,6 +87,8 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size);
  */
 int generation_numbers_enabled(struct repository *r);
 
+struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r);
+
 enum commit_graph_write_flags {
 	COMMIT_GRAPH_WRITE_APPEND     = (1 << 0),
 	COMMIT_GRAPH_WRITE_PROGRESS   = (1 << 1),
diff --git a/revision.c b/revision.c
index 6de29cdf7a..c45ed1076e 100644
--- a/revision.c
+++ b/revision.c
@@ -681,10 +681,7 @@ static void prepare_to_use_bloom_filter(struct rev_info *revs)
 
 	repo_parse_commit(revs->repo, revs->commits->item);
 
-	if (!revs->repo->objects->commit_graph)
-		return;
-
-	revs->bloom_filter_settings = revs->repo->objects->commit_graph->bloom_filter_settings;
+	revs->bloom_filter_settings = get_bloom_filter_settings(revs->repo);
 	if (!revs->bloom_filter_settings)
 		return;
 
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index c21cc160f3..c9f9bdf1ba 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -60,7 +60,7 @@ setup () {
 
 test_bloom_filters_used () {
 	log_args=$1
-	bloom_trace_prefix="statistics:{\"filter_not_present\":0,\"maybe\""
+	bloom_trace_prefix="statistics:{\"filter_not_present\":${2:-0},\"maybe\""
 	setup "$log_args" &&
 	grep -q "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.perf" &&
 	test_cmp log_wo_bloom log_w_bloom &&
@@ -134,8 +134,11 @@ test_expect_success 'setup - add commit-graph to the chain without Bloom filters
 	test_line_count = 2 .git/objects/info/commit-graphs/commit-graph-chain
 '
 
-test_expect_success 'Do not use Bloom filters if the latest graph does not have Bloom filters.' '
-	test_bloom_filters_not_used "-- A/B"
+test_expect_success 'use Bloom filters even if the latest graph does not have Bloom filters' '
+	# Ensure that the number of empty filters is equal to the number of
+	# filters in the latest graph layer to prove that they are loaded (and
+	# ignored).
+	test_bloom_filters_used "-- A/B" 3
 '
 
 test_expect_success 'setup - add commit-graph to the chain with Bloom filters' '
diff --git a/t/t5324-split-commit-graph.sh b/t/t5324-split-commit-graph.sh
index 9b850ea907..5bdfd53ef9 100755
--- a/t/t5324-split-commit-graph.sh
+++ b/t/t5324-split-commit-graph.sh
@@ -425,4 +425,17 @@ done <<\EOF
 0600 -r--------
 EOF
 
+test_expect_success '--split=replace with partial Bloom data' '
+	rm -rf $graphdir $infodir/commit-graph &&
+	git reset --hard commits/3 &&
+	git rev-list -1 HEAD~2 >a &&
+	git rev-list -1 HEAD~1 >b &&
+	git commit-graph write --split=no-merge --stdin-commits --changed-paths <a &&
+	git commit-graph write --split=no-merge --stdin-commits <b &&
+	git commit-graph write --split=replace --stdin-commits --changed-paths <c &&
+	ls $graphdir/graph-*.graph >graph-files &&
+	test_line_count = 1 graph-files &&
+	verify_chain_files_exist $graphdir
+'
+
 test_done

diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index c9f9bdf1ba..fe19f6a60c 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -53,7 +53,7 @@ sane_unset GIT_TRACE2_PERF_BRIEF
 sane_unset GIT_TRACE2_CONFIG_PARAMS
 
 setup () {
-	rm "$TRASH_DIRECTORY/trace.perf"
+	rm -f "$TRASH_DIRECTORY/trace.perf" &&
 	git -c core.commitGraph=false log --pretty="format:%s" $1 >log_wo_bloom &&
 	GIT_TRACE2_PERF="$TRASH_DIRECTORY/trace.perf" git -c core.commitGraph=true log --pretty="format:%s" $1 >log_w_bloom
 }

bloom.c, diff.h, t/t4216-log-bloom.sh, tree-diff.c

diff --git a/bloom.c b/bloom.c
index 0cf1962dc5..ed54e96e57 100644
--- a/bloom.c
+++ b/bloom.c
@@ -222,7 +222,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 		diff_tree_oid(NULL, &c->object.oid, "", &diffopt);
 	diffcore_std(&diffopt);
 
-	if (diffopt.num_changes <= settings->max_changed_paths) {
+	if (diff_queued_diff.nr <= settings->max_changed_paths) {
 		struct hashmap pathmap;
 		struct pathmap_hash_entry *e;
 		struct hashmap_iter iter;
@@ -259,6 +259,9 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 			diff_free_filepair(diff_queued_diff.queue[i]);
 		}
 
+		if (hashmap_get_size(&pathmap) > settings->max_changed_paths)
+			goto cleanup;
+
 		filter->len = (hashmap_get_size(&pathmap) * settings->bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
 		filter->data = xcalloc(filter->len, sizeof(unsigned char));
 
@@ -268,6 +271,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 			add_key_to_filter(&key, filter, settings);
 		}
 
+	cleanup:
 		hashmap_free_entries(&pathmap, struct pathmap_hash_entry, entry);
 	} else {
 		for (i = 0; i < diff_queued_diff.nr; i++)
diff --git a/diff.h b/diff.h
index e0c0af6286..1d32b71885 100644
--- a/diff.h
+++ b/diff.h
@@ -287,8 +287,6 @@ struct diff_options {
 
 	/* If non-zero, then stop computing after this many changes. */
 	int max_changes;
-	/* For internal use only. */
-	int num_changes;
 
 	int ita_invisible_in_index;
 /* white-space error highlighting */
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index eb2bcc51f0..21b67677ef 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -177,20 +177,87 @@ test_expect_success 'persist filter settings' '
 '
 
 test_expect_success 'correctly report changes over limit' '
-	git init 513changes &&
+	git init limits &&
 	(
-		cd 513changes &&
-		for i in $(test_seq 1 513)
+		cd limits &&
+		mkdir d &&
+		mkdir d/e &&
+
+		for i in $(test_seq 1 2)
 		do
-			echo $i >file$i.txt || return 1
+			printf $i >d/file$i.txt &&
+			printf $i >d/e/file$i.txt || return 1
 		done &&
-		git add . &&
+
+		mkdir mode &&
+		printf bash >mode/script.sh &&
+
+		mkdir foo &&
+		touch foo/bar &&
+		touch foo.txt &&
+
+		git add d foo foo.txt mode &&
 		git commit -m "files" &&
-		git commit-graph write --reachable --changed-paths &&
-		for i in $(test_seq 1 513)
+
+		# Commit has 7 file and 4 directory adds
+		GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=10 \
+			GIT_TRACE2_EVENT="$(pwd)/trace" \
+			git commit-graph write --reachable --changed-paths &&
+		grep "\"max_changed_paths\":10" trace &&
+		grep "\"filter_found_large\":1" trace &&
+
+		for path in $(git ls-tree -r --name-only HEAD)
 		do
-			git -c core.commitGraph=false log -- file$i.txt >expect &&
-			git log -- file$i.txt >actual &&
+			git -c commitGraph.readChangedPaths=false log \
+				-- $path >expect &&
+			git log -- $path >actual &&
+			test_cmp expect actual || return 1
+		done &&
+
+		# Make a variety of path changes
+		printf new1 >d/e/file1.txt &&
+		printf new2 >d/file2.txt &&
+		rm d/e/file2.txt &&
+		rm -r foo &&
+		printf text >foo &&
+		mkdir f &&
+		printf new1 >f/file1.txt &&
+
+		# including a mode-only change (counts as modified)
+		git update-index --chmod=+x mode/script.sh &&
+
+		git add foo d f &&
+		git commit -m "complicated" &&
+
+		# start from scratch and rebuild
+		rm -f .git/objects/info/commit-graph &&
+		GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=10 \
+			GIT_TRACE2_EVENT="$(pwd)/trace-edit" \
+			git commit-graph write --reachable --changed-paths &&
+		grep "\"max_changed_paths\":10" trace-edit &&
+		grep "\"filter_found_large\":2" trace-edit &&
+
+		for path in $(git ls-tree -r --name-only HEAD)
+		do
+			git -c commitGraph.readChangedPaths=false log \
+				-- $path >expect &&
+			git log -- $path >actual &&
+			test_cmp expect actual || return 1
+		done &&
+
+		# start from scratch and rebuild
+		rm -f .git/objects/info/commit-graph &&
+		GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=11 \
+			GIT_TRACE2_EVENT="$(pwd)/trace-update" \
+			git commit-graph write --reachable --changed-paths &&
+		grep "\"max_changed_paths\":11" trace-update &&
+		grep "\"filter_found_large\":0" trace-update &&
+
+		for path in $(git ls-tree -r --name-only HEAD)
+		do
+			git -c commitGraph.readChangedPaths=false log \
+				-- $path >expect &&
+			git log -- $path >actual &&
 			test_cmp expect actual || return 1
 		done
 	)
diff --git a/tree-diff.c b/tree-diff.c
index 6ebad1a46f..7cebbb327e 100644
--- a/tree-diff.c
+++ b/tree-diff.c
@@ -434,7 +434,7 @@ static struct combine_diff_path *ll_diff_tree_paths(
 		if (diff_can_quit_early(opt))
 			break;
 
-		if (opt->max_changes && opt->num_changes > opt->max_changes)
+		if (opt->max_changes && diff_queued_diff.nr > opt->max_changes)
 			break;
 
 		if (opt->pathspec.nr) {
@@ -521,7 +521,6 @@ static struct combine_diff_path *ll_diff_tree_paths(
 
 			/* t↓ */
 			update_tree_entry(&t);
-			opt->num_changes++;
 		}
 
 		/* t > p[imin] */
@@ -539,7 +538,6 @@ static struct combine_diff_path *ll_diff_tree_paths(
 		skip_emit_tp:
 			/* ∀ pi=p[imin]  pi↓ */
 			update_tp_entries(tp, nparent);
-			opt->num_changes++;
 		}
 	}
 
@@ -557,7 +555,6 @@ struct combine_diff_path *diff_tree_paths(
 	const struct object_id **parents_oid, int nparent,
 	struct strbuf *base, struct diff_options *opt)
 {
-	opt->num_changes = 0;
 	p = ll_diff_tree_paths(p, oid, parents_oid, nparent, base, opt);
 
 	/*

diff --git a/commit-graph.c b/commit-graph.c
index 48d4697f54..0d70545149 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -79,10 +79,18 @@ static void set_commit_pos(struct repository *r, const struct object_id *oid)
 	*commit_pos_at(&commit_pos, commit) = max_pos++;
 }
 
-static int commit_pos_cmp(const void *va, const void *vb)
+struct packed_commit_list {
+	struct commit **list;
+	int nr;
+	int alloc;
+};
+
+static int commit_pos_cmp(const void *va, const void *vb, void *ctx)
 {
-	const struct commit *a = *(const struct commit **)va;
-	const struct commit *b = *(const struct commit **)vb;
+	struct packed_commit_list *commits = ctx;
+
+	const struct commit *a = commits->list[*(int *)va];
+	const struct commit *b = commits->list[*(int *)vb];
 	return commit_pos_at(&commit_pos, a) -
 	       commit_pos_at(&commit_pos, b);
 }
@@ -139,10 +147,12 @@ static struct commit_graph_data *commit_graph_data_at(const struct commit *c)
 	return data;
 }
 
-static int commit_gen_cmp(const void *va, const void *vb)
+static int commit_gen_cmp(const void *va, const void *vb, void *ctx)
 {
-	const struct commit *a = *(const struct commit **)va;
-	const struct commit *b = *(const struct commit **)vb;
+	struct packed_commit_list *commits = ctx;
+
+	const struct commit *a = commits->list[*(int *)va];
+	const struct commit *b = commits->list[*(int *)vb];
 
 	uint32_t generation_a = commit_graph_generation(a);
 	uint32_t generation_b = commit_graph_generation(b);
@@ -922,11 +932,6 @@ struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit
 	return get_commit_tree_in_graph_one(r, r->objects->commit_graph, c);
 }
 
-struct packed_commit_list {
-	struct commit **list;
-	int nr;
-	int alloc;
-};
 
 struct packed_oid_list {
 	struct object_id *list;
@@ -1408,7 +1413,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 {
 	int i;
 	struct progress *progress = NULL;
-	struct commit **sorted_commits;
+	int *sorted_commits;
 
 	init_bloom_filters();
 
@@ -1418,16 +1423,16 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 			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++)
+		sorted_commits[i] = i;
+	QSORT_S(sorted_commits, ctx->commits.nr,
+		ctx->order_by_pack ? commit_pos_cmp : commit_gen_cmp,
+		&ctx->commits);
 
 	for (i = 0; i < ctx->commits.nr; i++) {
 		int computed = 0;
-		struct commit *c = sorted_commits[i];
+		int pos = sorted_commits[i];
+		struct commit *c = ctx->commits.list[pos];
 		struct bloom_filter *filter = get_or_compute_bloom_filter(
 			ctx->r,
 			c,

bloom.c, bloom.h, commit-graph.c, t/helper/test-bloom.c

diff --git a/bloom.c b/bloom.c
index a8a21762f4..0cf1962dc5 100644
--- a/bloom.c
+++ b/bloom.c
@@ -180,13 +180,12 @@ static int pathmap_cmp(const void *hashmap_cmp_fn_data,
 struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 						 struct commit *c,
 						 int compute_if_not_present,
+						 const struct bloom_filter_settings *settings,
 						 int *computed)
 {
 	struct bloom_filter *filter;
-	struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
 	int i;
 	struct diff_options diffopt;
-	int max_changes = 512;
 
 	if (computed)
 		*computed = 0;
@@ -211,7 +210,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 	repo_diff_setup(r, &diffopt);
 	diffopt.flags.recursive = 1;
 	diffopt.detect_rename = 0;
-	diffopt.max_changes = max_changes;
+	diffopt.max_changes = settings->max_changed_paths;
 	diff_setup_done(&diffopt);
 
 	/* ensure commit is parsed so we have parent information */
@@ -223,7 +222,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 		diff_tree_oid(NULL, &c->object.oid, "", &diffopt);
 	diffcore_std(&diffopt);
 
-	if (diffopt.num_changes <= max_changes) {
+	if (diffopt.num_changes <= settings->max_changed_paths) {
 		struct hashmap pathmap;
 		struct pathmap_hash_entry *e;
 		struct hashmap_iter iter;
@@ -260,13 +259,13 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 			diff_free_filepair(diff_queued_diff.queue[i]);
 		}
 
-		filter->len = (hashmap_get_size(&pathmap) * settings.bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
+		filter->len = (hashmap_get_size(&pathmap) * settings->bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
 		filter->data = xcalloc(filter->len, sizeof(unsigned char));
 
 		hashmap_for_each_entry(&pathmap, &iter, e, entry) {
 			struct bloom_key key;
-			fill_bloom_key(e->path, strlen(e->path), &key, &settings);
-			add_key_to_filter(&key, filter, &settings);
+			fill_bloom_key(e->path, strlen(e->path), &key, settings);
+			add_key_to_filter(&key, filter, settings);
 		}
 
 		hashmap_free_entries(&pathmap, struct pathmap_hash_entry, entry);
diff --git a/bloom.h b/bloom.h
index c4107a6415..2353c74a24 100644
--- a/bloom.h
+++ b/bloom.h
@@ -92,11 +92,12 @@ void init_bloom_filters(void);
 struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 						 struct commit *c,
 						 int compute_if_not_present,
+						 const struct bloom_filter_settings *settings,
 						 int *computed);
 
 #define DEFAULT_BLOOM_MAX_CHANGES 512
 #define get_bloom_filter(r, c) get_or_compute_bloom_filter( \
-	(r), (c), 0, NULL)
+	(r), (c), 0, NULL, NULL)
 
 int bloom_filter_contains(const struct bloom_filter *filter,
 			  const struct bloom_key *key,
diff --git a/commit-graph.c b/commit-graph.c
index ba2a2cfb22..48d4697f54 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1432,6 +1432,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 			ctx->r,
 			c,
 			1,
+			ctx->bloom_settings,
 			&computed);
 		if (computed) {
 			ctx->count_bloom_filter_computed++;
@@ -1688,17 +1689,6 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	int num_chunks = 3;
 	uint64_t chunk_offset;
 	struct object_id file_hash;
-	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);
-		bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS",
-							  bloom_settings.max_changed_paths);
-		ctx->bloom_settings = &bloom_settings;
-	}
 
 	if (ctx->split) {
 		struct strbuf tmp_file = STRBUF_INIT;
@@ -2144,6 +2134,7 @@ int write_commit_graph(struct object_directory *odb,
 	uint32_t i, count_distinct = 0;
 	int res = 0;
 	int replace = 0;
+	struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
 
 	if (!commit_graph_compatible(the_repository))
 		return 0;
@@ -2157,6 +2148,14 @@ int write_commit_graph(struct object_directory *odb,
 	ctx->split_opts = split_opts;
 	ctx->total_bloom_filter_data_size = 0;
 
+	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);
+	bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS",
+							 bloom_settings.max_changed_paths);
+	ctx->bloom_settings = &bloom_settings;
+
 	if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS)
 		ctx->changed_paths = 1;
 	if (!(flags & COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS)) {
diff --git a/t/helper/test-bloom.c b/t/helper/test-bloom.c
index 531af439c2..4af949164c 100644
--- a/t/helper/test-bloom.c
+++ b/t/helper/test-bloom.c
@@ -40,6 +40,7 @@ static void get_bloom_filter_for_commit(const struct object_id *commit_oid)
 	setup_git_directory();
 	c = lookup_commit(the_repository, commit_oid);
 	filter = get_or_compute_bloom_filter(the_repository, c, 1,
+					     &settings,
 					     NULL);
 	print_bloom_filter(filter);
 }

blame.c, bloom.c, bloom.h, commit-graph.c, line-log.c, revision.c, t/helper/test-bloom.c

diff --git a/blame.c b/blame.c
index 3e5f8787bc..756285fca7 100644
--- a/blame.c
+++ b/blame.c
@@ -1275,7 +1275,7 @@ static int maybe_changed_path(struct repository *r,
 	if (commit_graph_generation(origin->commit) == GENERATION_NUMBER_INFINITY)
 		return 1;
 
-	filter = get_bloom_filter(r, origin->commit, 0);
+	filter = get_bloom_filter(r, origin->commit);
 
 	if (!filter)
 		return 1;
diff --git a/bloom.c b/bloom.c
index cd9380ac62..a8a21762f4 100644
--- a/bloom.c
+++ b/bloom.c
@@ -177,9 +177,10 @@ static int pathmap_cmp(const void *hashmap_cmp_fn_data,
 	return strcmp(e1->path, e2->path);
 }
 
-struct bloom_filter *get_bloom_filter(struct repository *r,
-				      struct commit *c,
-				      int compute_if_not_present)
+struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
+						 struct commit *c,
+						 int compute_if_not_present,
+						 int *computed)
 {
 	struct bloom_filter *filter;
 	struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
@@ -187,6 +188,9 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 	struct diff_options diffopt;
 	int max_changes = 512;
 
+	if (computed)
+		*computed = 0;
+
 	if (!bloom_filters.slab_size)
 		return NULL;
 
@@ -273,6 +277,9 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 		filter->len = 0;
 	}
 
+	if (computed)
+		*computed = 1;
+
 	free(diff_queued_diff.queue);
 	DIFF_QUEUE_CLEAR(&diff_queued_diff);
 
diff --git a/bloom.h b/bloom.h
index 0b9b59a6fe..c4107a6415 100644
--- a/bloom.h
+++ b/bloom.h
@@ -89,9 +89,14 @@ void add_key_to_filter(const struct bloom_key *key,
 
 void init_bloom_filters(void);
 
-struct bloom_filter *get_bloom_filter(struct repository *r,
-				      struct commit *c,
-				      int compute_if_not_present);
+struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
+						 struct commit *c,
+						 int compute_if_not_present,
+						 int *computed);
+
+#define DEFAULT_BLOOM_MAX_CHANGES 512
+#define get_bloom_filter(r, c) get_or_compute_bloom_filter( \
+	(r), (c), 0, NULL)
 
 int bloom_filter_contains(const struct bloom_filter *filter,
 			  const struct bloom_key *key,
diff --git a/commit-graph.c b/commit-graph.c
index 86dd4b979e..ba2a2cfb22 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -964,6 +964,9 @@ struct write_commit_graph_context {
 	const struct split_commit_graph_opts *split_opts;
 	size_t total_bloom_filter_data_size;
 	const struct bloom_filter_settings *bloom_settings;
+
+	int count_bloom_filter_found_large;
+	int count_bloom_filter_computed;
 };
 
 static int write_graph_chunk_fanout(struct hashfile *f,
@@ -1175,7 +1178,7 @@ static int write_graph_chunk_bloom_indexes(struct hashfile *f,
 	uint32_t cur_pos = 0;
 
 	while (list < last) {
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list);
 		size_t len = filter ? filter->len : 0;
 		cur_pos += len;
 		display_progress(ctx->progress, ++ctx->progress_cnt);
@@ -1215,7 +1218,7 @@ static int write_graph_chunk_bloom_data(struct hashfile *f,
 	hashwrite_be32(f, ctx->bloom_settings->bits_per_entry);
 
 	while (list < last) {
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list);
 		size_t len = filter ? filter->len : 0;
 
 		display_progress(ctx->progress, ++ctx->progress_cnt);
@@ -1385,6 +1388,22 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 	stop_progress(&ctx->progress);
 }
 
+static void trace2_bloom_filter_write_statistics(struct write_commit_graph_context *ctx)
+{
+	struct json_writer jw = JSON_WRITER_INIT;
+
+	jw_object_begin(&jw, 0);
+	jw_object_intmax(&jw, "filter_found_large",
+			 ctx->count_bloom_filter_found_large);
+	jw_object_intmax(&jw, "filter_computed",
+			 ctx->count_bloom_filter_computed);
+	jw_end(&jw);
+
+	trace2_data_json("commit-graph", the_repository, "bloom_statistics", &jw);
+
+	jw_release(&jw);
+}
+
 static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 {
 	int i;
@@ -1407,12 +1426,25 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 		QSORT(sorted_commits, ctx->commits.nr, commit_gen_cmp);
 
 	for (i = 0; i < ctx->commits.nr; i++) {
+		int computed = 0;
 		struct commit *c = sorted_commits[i];
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, c, 1);
+		struct bloom_filter *filter = get_or_compute_bloom_filter(
+			ctx->r,
+			c,
+			1,
+			&computed);
+		if (computed) {
+			ctx->count_bloom_filter_computed++;
+			if (filter && !filter->len)
+				ctx->count_bloom_filter_found_large++;
+		}
 		ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
 		display_progress(progress, i + 1);
 	}
 
+	if (trace2_is_enabled())
+		trace2_bloom_filter_write_statistics(ctx);
+
 	free(sorted_commits);
 	stop_progress(&progress);
 }
diff --git a/line-log.c b/line-log.c
index c53692834d..9e58fd185a 100644
--- a/line-log.c
+++ b/line-log.c
@@ -1159,7 +1159,7 @@ static int bloom_filter_check(struct rev_info *rev,
 		return 1;
 
 	if (!rev->bloom_filter_settings ||
-	    !(filter = get_bloom_filter(rev->repo, commit, 0)))
+	    !(filter = get_bloom_filter(rev->repo, commit)))
 		return 1;
 
 	if (!range)
diff --git a/revision.c b/revision.c
index c45ed1076e..b7ec712755 100644
--- a/revision.c
+++ b/revision.c
@@ -753,7 +753,7 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
 	if (commit_graph_generation(commit) == GENERATION_NUMBER_INFINITY)
 		return -1;
 
-	filter = get_bloom_filter(revs->repo, commit, 0);
+	filter = get_bloom_filter(revs->repo, commit);
 
 	if (!filter) {
 		count_bloom_filter_not_present++;
diff --git a/t/helper/test-bloom.c b/t/helper/test-bloom.c
index f0aa80b98e..531af439c2 100644
--- a/t/helper/test-bloom.c
+++ b/t/helper/test-bloom.c
@@ -39,7 +39,8 @@ static void get_bloom_filter_for_commit(const struct object_id *commit_oid)
 	struct bloom_filter *filter;
 	setup_git_directory();
 	c = lookup_commit(the_repository, commit_oid);
-	filter = get_bloom_filter(the_repository, c, 1);
+	filter = get_or_compute_bloom_filter(the_repository, c, 1,
+					     NULL);
 	print_bloom_filter(filter);
 }
 

Documentation/technical/commit-graph-format.txt, bloom.h, commit-graph.c, commit-graph.h, t/t4216-log-bloom.sh

diff --git a/Documentation/technical/commit-graph-format.txt b/Documentation/technical/commit-graph-format.txt
index 440541045d..5f2d9ab4d7 100644
--- a/Documentation/technical/commit-graph-format.txt
+++ b/Documentation/technical/commit-graph-format.txt
@@ -123,6 +123,18 @@ CHUNK DATA:
       of length zero.
     * The BDAT chunk is present if and only if BIDX is present.
 
+  Large Bloom Filters (ID: {'B', 'F', 'X', 'L'}) [Optional]
+    * It starts with a 32-bit unsigned integer specifying the maximum number of
+      changed-paths that can be stored in a single Bloom filter.
+    * It then contains a list of 64-bit words (the length of this list is
+      determined by the width of the chunk) which is a bitmap. The 'i'th bit is
+      set exactly when the 'i'th commit in the graph has a changed-path Bloom
+      filter with zero entries (either because the commit is empty, or because
+      it contains more than 512 changed paths).
+    * The BFXL chunk is present only when the BIDX and BDAT chunks are
+      also present.
+
+
   Base Graphs List (ID: {'B', 'A', 'S', 'E'}) [Optional]
       This list of H-byte hashes describe a set of B commit-graph files that
       form a commit-graph chain. The graph position for the ith commit in this
diff --git a/bloom.h b/bloom.h
index 2353c74a24..73238276bc 100644
--- a/bloom.h
+++ b/bloom.h
@@ -33,7 +33,7 @@ struct bloom_filter_settings {
 	 * The maximum number of changed paths per commit
 	 * before declaring a Bloom filter to be too-large.
 	 *
-	 * Not written to the commit-graph file.
+	 * Written to the 'BFXL' chunk (instead of 'BDAT').
 	 */
 	uint32_t max_changed_paths;
 };
diff --git a/commit-graph.c b/commit-graph.c
index 8964453433..1fee49d171 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -41,8 +41,9 @@ void git_test_write_commit_graph_or_die(void)
 #define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
 #define GRAPH_CHUNKID_BLOOMINDEXES 0x42494458 /* "BIDX" */
 #define GRAPH_CHUNKID_BLOOMDATA 0x42444154 /* "BDAT" */
+#define GRAPH_CHUNKID_BLOOMLARGE 0x4246584c /* "BFXL" */
 #define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */
-#define MAX_NUM_CHUNKS 7
+#define MAX_NUM_CHUNKS 8
 
 #define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
 
@@ -429,6 +430,19 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 				graph->bloom_filter_settings->bits_per_entry = get_be32(data + chunk_offset + 8);
 			}
 			break;
+
+		case GRAPH_CHUNKID_BLOOMLARGE:
+			if (graph->chunk_bloom_large_filters)
+				chunk_repeated = 1;
+			else if (r->settings.commit_graph_read_changed_paths) {
+				graph->bloom_large_to_alloc = get_be64(chunk_lookup + 4)
+							      - chunk_offset - sizeof(uint32_t);
+
+				graph->bloom_large.word_alloc = 0; /* populate when necessary */
+				graph->chunk_bloom_large_filters = data + chunk_offset + sizeof(uint32_t);
+				graph->bloom_filter_settings->max_changed_paths = get_be32(data + chunk_offset);
+			}
+			break;
 		}
 
 		if (chunk_repeated) {
@@ -443,6 +457,7 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 		/* We need both the bloom chunks to exist together. Else ignore the data */
 		graph->chunk_bloom_indexes = NULL;
 		graph->chunk_bloom_data = NULL;
+		graph->chunk_bloom_large_filters = NULL;
 		FREE_AND_NULL(graph->bloom_filter_settings);
 	}
 
@@ -932,6 +947,31 @@ struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit
 	return get_commit_tree_in_graph_one(r, r->objects->commit_graph, c);
 }
 
+static int get_bloom_filter_large_in_graph(struct commit_graph *g,
+					   const struct commit *c)
+{
+	uint32_t graph_pos = commit_graph_position(c);
+	if (graph_pos == COMMIT_NOT_FROM_GRAPH)
+		return 0;
+
+	while (g && graph_pos < g->num_commits_in_base)
+		g = g->base_graph;
+
+	if (!g || !g->bloom_large_to_alloc)
+		return 0;
+
+	if (!g->bloom_large.word_alloc) {
+		size_t i;
+		g->bloom_large.word_alloc = g->bloom_large_to_alloc;
+		g->bloom_large.words = xmalloc(g->bloom_large_to_alloc * sizeof(eword_t));
+
+		for (i = 0; i < g->bloom_large_to_alloc; i++)
+			g->bloom_large.words[i] = get_be64(g->chunk_bloom_large_filters
+							   + i * sizeof(eword_t));
+	}
+
+	return bitmap_get(&g->bloom_large, graph_pos - g->num_commits_in_base);
+}
 
 struct packed_oid_list {
 	struct object_id *list;
@@ -970,8 +1010,10 @@ struct write_commit_graph_context {
 	size_t total_bloom_filter_data_size;
 	const struct bloom_filter_settings *bloom_settings;
 
+	int count_bloom_filter_known_large;
 	int count_bloom_filter_found_large;
 	int count_bloom_filter_computed;
+	struct bitmap *bloom_large;
 };
 
 static int write_graph_chunk_fanout(struct hashfile *f,
@@ -1235,6 +1277,23 @@ static int write_graph_chunk_bloom_data(struct hashfile *f,
 	return 0;
 }
 
+static int write_graph_chunk_bloom_large(struct hashfile *f,
+					 struct write_commit_graph_context *ctx)
+{
+	size_t i, alloc = ctx->commits.nr / BITS_IN_EWORD;
+	if (ctx->commits.nr % BITS_IN_EWORD)
+		alloc++;
+	if (alloc > ctx->bloom_large->word_alloc)
+		BUG("write_graph_chunk_bloom_large: bitmap not large enough");
+
+	trace2_region_enter("commit-graph", "bloom_large", ctx->r);
+	hashwrite_be32(f, ctx->bloom_settings->max_changed_paths);
+	for (i = 0; i < ctx->bloom_large->word_alloc; i++)
+		hashwrite_be64(f, ctx->bloom_large->words[i]);
+	trace2_region_leave("commit-graph", "bloom_large", ctx->r);
+	return 0;
+}
+
 static int oid_compare(const void *_a, const void *_b)
 {
 	const struct object_id *a = (const struct object_id *)_a;
@@ -1398,6 +1457,8 @@ static void trace2_bloom_filter_write_statistics(struct write_commit_graph_conte
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
+	jw_object_intmax(&jw, "filter_known_large",
+			 ctx->count_bloom_filter_known_large);
 	jw_object_intmax(&jw, "filter_found_large",
 			 ctx->count_bloom_filter_found_large);
 	jw_object_intmax(&jw, "filter_computed",
@@ -1416,6 +1477,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 	int *sorted_commits;
 
 	init_bloom_filters();
+	ctx->bloom_large = bitmap_word_alloc(ctx->commits.nr / BITS_IN_EWORD + 1);
 
 	if (ctx->report_progress)
 		progress = start_delayed_progress(
@@ -1430,21 +1492,28 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 		&ctx->commits);
 
 	for (i = 0; i < ctx->commits.nr; i++) {
-		int computed = 0;
 		int pos = sorted_commits[i];
 		struct commit *c = ctx->commits.list[pos];
-		struct bloom_filter *filter = get_or_compute_bloom_filter(
-			ctx->r,
-			c,
-			1,
-			ctx->bloom_settings,
-			&computed);
-		if (computed) {
-			ctx->count_bloom_filter_computed++;
-			if (filter && !filter->len)
-				ctx->count_bloom_filter_found_large++;
+		if (get_bloom_filter_large_in_graph(ctx->r->objects->commit_graph, c)) {
+			bitmap_set(ctx->bloom_large, pos);
+			ctx->count_bloom_filter_known_large++;
+		} else {
+			int computed = 0;
+			struct bloom_filter *filter = get_or_compute_bloom_filter(
+				ctx->r,
+				c,
+				1,
+				ctx->bloom_settings,
+				&computed);
+			if (computed) {
+				ctx->count_bloom_filter_computed++;
+				if (filter && !filter->len) {
+					bitmap_set(ctx->bloom_large, pos);
+					ctx->count_bloom_filter_found_large++;
+				}
+			}
+			ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
 		}
-		ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
 		display_progress(progress, i + 1);
 	}
 
@@ -1764,6 +1833,11 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 					  + ctx->total_bloom_filter_data_size;
 		chunks[num_chunks].write_fn = write_graph_chunk_bloom_data;
 		num_chunks++;
+		chunks[num_chunks].id = GRAPH_CHUNKID_BLOOMLARGE;
+		chunks[num_chunks].size = sizeof(eword_t) * ctx->bloom_large->word_alloc
+					+ sizeof(uint32_t);
+		chunks[num_chunks].write_fn = write_graph_chunk_bloom_large;
+		num_chunks++;
 	}
 	if (ctx->num_commit_graphs_after > 1) {
 		chunks[num_chunks].id = GRAPH_CHUNKID_BASE;
@@ -2503,6 +2577,7 @@ void free_commit_graph(struct commit_graph *g)
 	}
 	free(g->filename);
 	free(g->bloom_filter_settings);
+	bitmap_free(g->bloom_large);
 	free(g);
 }
 
diff --git a/commit-graph.h b/commit-graph.h
index d9acb22bac..f4fb996dd5 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -4,6 +4,7 @@
 #include "git-compat-util.h"
 #include "object-store.h"
 #include "oidset.h"
+#include "ewah/ewok.h"
 
 #define GIT_TEST_COMMIT_GRAPH "GIT_TEST_COMMIT_GRAPH"
 #define GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE "GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE"
@@ -71,6 +72,10 @@ struct commit_graph {
 	const unsigned char *chunk_base_graphs;
 	const unsigned char *chunk_bloom_indexes;
 	const unsigned char *chunk_bloom_data;
+	const unsigned char *chunk_bloom_large_filters;
+
+	size_t bloom_large_to_alloc;
+	struct bitmap bloom_large;
 
 	struct bloom_filter_settings *bloom_filter_settings;
 };
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index 21b67677ef..6859d85369 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -33,7 +33,7 @@ test_expect_success 'setup test - repo, commits, commit graph, log outputs' '
 	git commit-graph write --reachable --changed-paths
 '
 graph_read_expect () {
-	NUM_CHUNKS=5
+	NUM_CHUNKS=6
 	cat >expect <<- EOF
 	header: 43475048 1 1 $NUM_CHUNKS 0
 	num_commits: $1
@@ -262,5 +262,28 @@ test_expect_success 'correctly report changes over limit' '
 		done
 	)
 '
+test_bloom_filters_computed () {
+	commit_graph_args=$1
+	bloom_trace_prefix="{\"filter_known_large\":$2,\"filter_found_large\":$3,\"filter_computed\":$4"
+	rm -f "$TRASH_DIRECTORY/trace.event" &&
+	GIT_TRACE2_EVENT="$TRASH_DIRECTORY/trace.event" git commit-graph write $commit_graph_args &&
+	grep "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.event"
+}
+
+test_expect_success 'Bloom generation does not recompute too-large filters' '
+	(
+		cd limits &&
+
+		# start from scratch and rebuild
+		rm -f .git/objects/info/commit-graph &&
+		GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=10 \
+			git commit-graph write --reachable --changed-paths \
+			--split=replace &&
+		test_commit c1 filter &&
+
+		test_bloom_filters_computed "--reachable --changed-paths --split=replace" \
+			2 0 1
+	)
+'
 
 test_done

bloom.c, commit-graph.c, commit-graph.h

diff --git a/bloom.c b/bloom.c
index d0c0fd049d..8d07209c6b 100644
--- a/bloom.c
+++ b/bloom.c
@@ -52,7 +52,7 @@ static int load_bloom_filter_from_graph(struct commit_graph *g,
                start_index = 0;

        if ((start_index == end_index) &&
-           (g->bloom_large.word_alloc && !bitmap_get(&g->bloom_large, lex_pos))) {
+           (g->bloom_large && !bitmap_get(g->bloom_large, lex_pos))) {
                /*
                 * If the filter is zero-length, either (1) the filter has no
                 * changes, (2) the filter has too many changes, or (3) it

In either case, this will fix the bad free():

--- >8 ---

Subject: [PATCH] fixup! commit-graph: add large-filters bitmap chunk

Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 commit-graph.c | 18 ++++++++++--------
 commit-graph.h |  2 +-
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/commit-graph.c b/commit-graph.c
index 1fee49d171..add76f1824 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -438,7 +438,10 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 				graph->bloom_large_to_alloc = get_be64(chunk_lookup + 4)
 							      - chunk_offset - sizeof(uint32_t);

-				graph->bloom_large.word_alloc = 0; /* populate when necessary */
+				/*
+				 * leave 'bloom_large' uninitialized, and
+				 * populate when necessary
+				 */
 				graph->chunk_bloom_large_filters = data + chunk_offset + sizeof(uint32_t);
 				graph->bloom_filter_settings->max_changed_paths = get_be32(data + chunk_offset);
 			}
@@ -960,17 +963,15 @@ static int get_bloom_filter_large_in_graph(struct commit_graph *g,
 	if (!g || !g->bloom_large_to_alloc)
 		return 0;

-	if (!g->bloom_large.word_alloc) {
+	if (!g->bloom_large) {
 		size_t i;
-		g->bloom_large.word_alloc = g->bloom_large_to_alloc;
-		g->bloom_large.words = xmalloc(g->bloom_large_to_alloc * sizeof(eword_t));
-
+		g->bloom_large = bitmap_word_alloc(g->bloom_large_to_alloc);
 		for (i = 0; i < g->bloom_large_to_alloc; i++)
-			g->bloom_large.words[i] = get_be64(g->chunk_bloom_large_filters
-							   + i * sizeof(eword_t));
+			g->bloom_large->words[i] = get_be64(g->chunk_bloom_large_filters
+							    + i * sizeof(eword_t));
 	}

-	return bitmap_get(&g->bloom_large, graph_pos - g->num_commits_in_base);
+	return bitmap_get(g->bloom_large, graph_pos - g->num_commits_in_base);
 }

 struct packed_oid_list {
@@ -2360,6 +2361,7 @@ int write_commit_graph(struct object_directory *odb,
 	free(ctx->graph_name);
 	free(ctx->commits.list);
 	free(ctx->oids.list);
+	free(ctx->bloom_large);

 	if (ctx->commit_graph_filenames_after) {
 		for (i = 0; i < ctx->num_commit_graphs_after; i++) {
diff --git a/commit-graph.h b/commit-graph.h
index f4fb996dd5..b1ab86a3c8 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -75,7 +75,7 @@ struct commit_graph {
 	const unsigned char *chunk_bloom_large_filters;

 	size_t bloom_large_to_alloc;
-	struct bitmap bloom_large;
+	struct bitmap *bloom_large;

 	struct bloom_filter_settings *bloom_filter_settings;
 };
--
2.28.0.rc1.13.ge78abce653

commit-graph.c, commit-graph.h

diff --git a/commit-graph.c b/commit-graph.c
index 1fee49d171..384089be87 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -438,7 +438,10 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 				graph->bloom_large_to_alloc = get_be64(chunk_lookup + 4)
 							      - chunk_offset - sizeof(uint32_t);

-				graph->bloom_large.word_alloc = 0; /* populate when necessary */
+				/*
+				 * leave 'bloom_large' uninitialized, and
+				 * populate when necessary
+				 */
 				graph->chunk_bloom_large_filters = data + chunk_offset + sizeof(uint32_t);
 				graph->bloom_filter_settings->max_changed_paths = get_be32(data + chunk_offset);
 			}
@@ -960,17 +963,15 @@ static int get_bloom_filter_large_in_graph(struct commit_graph *g,
 	if (!g || !g->bloom_large_to_alloc)
 		return 0;

-	if (!g->bloom_large.word_alloc) {
+	if (!g->bloom_large) {
 		size_t i;
-		g->bloom_large.word_alloc = g->bloom_large_to_alloc;
-		g->bloom_large.words = xmalloc(g->bloom_large_to_alloc * sizeof(eword_t));
-
+		g->bloom_large = bitmap_word_alloc(g->bloom_large_to_alloc);
 		for (i = 0; i < g->bloom_large_to_alloc; i++)
-			g->bloom_large.words[i] = get_be64(g->chunk_bloom_large_filters
-							   + i * sizeof(eword_t));
+			g->bloom_large->words[i] = get_be64(g->chunk_bloom_large_filters
+							    + i * sizeof(eword_t));
 	}

-	return bitmap_get(&g->bloom_large, graph_pos - g->num_commits_in_base);
+	return bitmap_get(g->bloom_large, graph_pos - g->num_commits_in_base);
 }

 struct packed_oid_list {
@@ -2360,6 +2361,7 @@ int write_commit_graph(struct object_directory *odb,
 	free(ctx->graph_name);
 	free(ctx->commits.list);
 	free(ctx->oids.list);
+	bitmap_free(ctx->bloom_large);

 	if (ctx->commit_graph_filenames_after) {
 		for (i = 0; i < ctx->num_commit_graphs_after; i++) {
diff --git a/commit-graph.h b/commit-graph.h
index f4fb996dd5..b1ab86a3c8 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -75,7 +75,7 @@ struct commit_graph {
 	const unsigned char *chunk_bloom_large_filters;

 	size_t bloom_large_to_alloc;
-	struct bitmap bloom_large;
+	struct bitmap *bloom_large;

 	struct bloom_filter_settings *bloom_filter_settings;
 };
--
2.28.0.rc1.13.ge78abce653

commit-graph.c, csum-file.h, midx.c

diff --git a/commit-graph.c b/commit-graph.c
index 0d70545149..8964453433 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1784,12 +1784,8 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 
 	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(chunks[i].id);
-		chunk_write[1] = htonl(chunk_offset >> 32);
-		chunk_write[2] = htonl(chunk_offset & 0xffffffff);
-		hashwrite(f, chunk_write, 12);
+		hashwrite_be32(f, chunks[i].id);
+		hashwrite_be64(f, chunk_offset);
 
 		chunk_offset += chunks[i].size;
 	}
diff --git a/csum-file.h b/csum-file.h
index f9cbd317fb..b026ec7766 100644
--- a/csum-file.h
+++ b/csum-file.h
@@ -62,4 +62,10 @@ static inline void hashwrite_be32(struct hashfile *f, uint32_t data)
 	hashwrite(f, &data, sizeof(data));
 }
 
+static inline void hashwrite_be64(struct hashfile *f, uint64_t data)
+{
+	hashwrite_be32(f, data >> 32);
+	hashwrite_be32(f, data & 0xffffffffUL);
+}
+
 #endif
diff --git a/midx.c b/midx.c
index 6d1584ca51..8b33149ce4 100644
--- a/midx.c
+++ b/midx.c
@@ -775,8 +775,7 @@ static size_t write_midx_large_offsets(struct hashfile *f, uint32_t nr_large_off
 		if (!(offset >> 31))
 			continue;
 
-		hashwrite_be32(f, offset >> 32);
-		hashwrite_be32(f, offset & 0xffffffffUL);
+		hashwrite_be64(f, offset);
 		written += 2 * sizeof(uint32_t);
 
 		nr_large_offset--;

builtin/commit-graph.c, commit-graph.c, commit-graph.h

diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index ba5584463f..38f5f57d15 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -119,7 +119,7 @@ static int graph_verify(int argc, const char **argv)
 }
 
 extern int read_replace_refs;
-static struct split_commit_graph_opts split_opts;
+static struct commit_graph_opts write_opts;
 
 static int write_option_parse_split(const struct option *opt, const char *arg,
 				    int unset)
@@ -187,24 +187,24 @@ static int graph_write(int argc, const char **argv)
 		OPT_BOOL(0, "changed-paths", &opts.enable_changed_paths,
 			N_("enable computation for changed paths")),
 		OPT_BOOL(0, "progress", &opts.progress, N_("force progress reporting")),
-		OPT_CALLBACK_F(0, "split", &split_opts.flags, NULL,
+		OPT_CALLBACK_F(0, "split", &write_opts.flags, NULL,
 			N_("allow writing an incremental commit-graph file"),
 			PARSE_OPT_OPTARG | PARSE_OPT_NONEG,
 			write_option_parse_split),
-		OPT_INTEGER(0, "max-commits", &split_opts.max_commits,
+		OPT_INTEGER(0, "max-commits", &write_opts.max_commits,
 			N_("maximum number of commits in a non-base split commit-graph")),
-		OPT_INTEGER(0, "size-multiple", &split_opts.size_multiple,
+		OPT_INTEGER(0, "size-multiple", &write_opts.size_multiple,
 			N_("maximum ratio between two levels of a split commit-graph")),
-		OPT_EXPIRY_DATE(0, "expire-time", &split_opts.expire_time,
+		OPT_EXPIRY_DATE(0, "expire-time", &write_opts.expire_time,
 			N_("only expire files older than a given date-time")),
 		OPT_END(),
 	};
 
 	opts.progress = isatty(2);
 	opts.enable_changed_paths = -1;
-	split_opts.size_multiple = 2;
-	split_opts.max_commits = 0;
-	split_opts.expire_time = 0;
+	write_opts.size_multiple = 2;
+	write_opts.max_commits = 0;
+	write_opts.expire_time = 0;
 
 	trace2_cmd_mode("write");
 
@@ -232,7 +232,7 @@ static int graph_write(int argc, const char **argv)
 	odb = find_odb(the_repository, opts.obj_dir);
 
 	if (opts.reachable) {
-		if (write_commit_graph_reachable(odb, flags, &split_opts))
+		if (write_commit_graph_reachable(odb, flags, &write_opts))
 			return 1;
 		return 0;
 	}
@@ -261,7 +261,7 @@ static int graph_write(int argc, const char **argv)
 			       opts.stdin_packs ? &pack_indexes : NULL,
 			       opts.stdin_commits ? &commits : NULL,
 			       flags,
-			       &split_opts))
+			       &write_opts))
 		result = 1;
 
 cleanup:
diff --git a/commit-graph.c b/commit-graph.c
index 1fee49d171..82fca07579 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1006,7 +1006,7 @@ struct write_commit_graph_context {
 		 changed_paths:1,
 		 order_by_pack:1;
 
-	const struct split_commit_graph_opts *split_opts;
+	const struct commit_graph_opts *opts;
 	size_t total_bloom_filter_data_size;
 	const struct bloom_filter_settings *bloom_settings;
 
@@ -1347,8 +1347,8 @@ 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;
+	enum commit_graph_split_flags flags = ctx->opts ?
+		ctx->opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	if (ctx->report_progress)
 		ctx->progress = start_delayed_progress(
@@ -1548,7 +1548,7 @@ static int add_ref_to_set(const char *refname,
 
 int write_commit_graph_reachable(struct object_directory *odb,
 				 enum commit_graph_write_flags flags,
-				 const struct split_commit_graph_opts *split_opts)
+				 const struct commit_graph_opts *opts)
 {
 	struct oidset commits = OIDSET_INIT;
 	struct refs_cb_data data;
@@ -1565,7 +1565,7 @@ int write_commit_graph_reachable(struct object_directory *odb,
 	stop_progress(&data.progress);
 
 	result = write_commit_graph(odb, NULL, &commits,
-				    flags, split_opts);
+				    flags, opts);
 
 	oidset_clear(&commits);
 	return result;
@@ -1680,8 +1680,8 @@ 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;
+	enum commit_graph_split_flags flags = ctx->opts ?
+		ctx->opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	ctx->num_extra_edges = 0;
 	if (ctx->report_progress)
@@ -1967,13 +1967,13 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 	int max_commits = 0;
 	int size_mult = 2;
 
-	if (ctx->split_opts) {
-		max_commits = ctx->split_opts->max_commits;
+	if (ctx->opts) {
+		max_commits = ctx->opts->max_commits;
 
-		if (ctx->split_opts->size_multiple)
-			size_mult = ctx->split_opts->size_multiple;
+		if (ctx->opts->size_multiple)
+			size_mult = ctx->opts->size_multiple;
 
-		flags = ctx->split_opts->flags;
+		flags = ctx->opts->flags;
 	}
 
 	g = ctx->r->objects->commit_graph;
@@ -2151,8 +2151,8 @@ static void expire_commit_graphs(struct write_commit_graph_context *ctx)
 	size_t dirnamelen;
 	timestamp_t expire_time = time(NULL);
 
-	if (ctx->split_opts && ctx->split_opts->expire_time)
-		expire_time = ctx->split_opts->expire_time;
+	if (ctx->opts && ctx->opts->expire_time)
+		expire_time = ctx->opts->expire_time;
 	if (!ctx->split) {
 		char *chain_file_name = get_chain_filename(ctx->odb);
 		unlink(chain_file_name);
@@ -2203,7 +2203,7 @@ int write_commit_graph(struct object_directory *odb,
 		       struct string_list *pack_indexes,
 		       struct oidset *commits,
 		       enum commit_graph_write_flags flags,
-		       const struct split_commit_graph_opts *split_opts)
+		       const struct commit_graph_opts *opts)
 {
 	struct write_commit_graph_context *ctx;
 	uint32_t i, count_distinct = 0;
@@ -2220,7 +2220,7 @@ 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->split_opts = split_opts;
+	ctx->opts = opts;
 	ctx->total_bloom_filter_data_size = 0;
 
 	bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY",
@@ -2268,15 +2268,15 @@ int write_commit_graph(struct object_directory *odb,
 			}
 		}
 
-		if (ctx->split_opts)
-			replace = ctx->split_opts->flags & COMMIT_GRAPH_SPLIT_REPLACE;
+		if (ctx->opts)
+			replace = ctx->opts->flags & COMMIT_GRAPH_SPLIT_REPLACE;
 	}
 
 	ctx->approx_nr_objects = approximate_object_count();
 	ctx->oids.alloc = ctx->approx_nr_objects / 32;
 
-	if (ctx->split && split_opts && ctx->oids.alloc > split_opts->max_commits)
-		ctx->oids.alloc = split_opts->max_commits;
+	if (ctx->split && opts && ctx->oids.alloc > opts->max_commits)
+		ctx->oids.alloc = opts->max_commits;
 
 	if (ctx->append) {
 		prepare_commit_graph_one(ctx->r, ctx->odb);
diff --git a/commit-graph.h b/commit-graph.h
index f4fb996dd5..1d147b7b76 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -110,7 +110,7 @@ enum commit_graph_split_flags {
 	COMMIT_GRAPH_SPLIT_REPLACE          = 2
 };
 
-struct split_commit_graph_opts {
+struct commit_graph_opts {
 	int size_multiple;
 	int max_commits;
 	timestamp_t expire_time;
@@ -125,12 +125,12 @@ struct split_commit_graph_opts {
  */
 int write_commit_graph_reachable(struct object_directory *odb,
 				 enum commit_graph_write_flags flags,
-				 const struct split_commit_graph_opts *split_opts);
+				 const struct commit_graph_opts *opts);
 int write_commit_graph(struct object_directory *odb,
 		       struct string_list *pack_indexes,
 		       struct oidset *commits,
 		       enum commit_graph_write_flags flags,
-		       const struct split_commit_graph_opts *split_opts);
+		       const struct commit_graph_opts *opts);
 
 #define COMMIT_GRAPH_VERIFY_SHALLOW	(1 << 0)
 

builtin/commit-graph.c, commit-graph.c, commit-graph.h, fuzz-commit-graph.c

diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index 523501f217..ba5584463f 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -106,7 +106,7 @@ static int graph_verify(int argc, const char **argv)
 	FREE_AND_NULL(graph_name);
 
 	if (open_ok)
-		graph = load_commit_graph_one_fd_st(fd, &st, odb);
+		graph = load_commit_graph_one_fd_st(the_repository, fd, &st, odb);
 	else
 		graph = read_commit_graph_one(the_repository, odb);
 
diff --git a/commit-graph.c b/commit-graph.c
index d4b06811be..0c1030641c 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -224,7 +224,8 @@ int open_commit_graph(const char *graph_file, int *fd, struct stat *st)
 	return 1;
 }
 
-struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st,
+struct commit_graph *load_commit_graph_one_fd_st(struct repository *r,
+						 int fd, struct stat *st,
 						 struct object_directory *odb)
 {
 	void *graph_map;
@@ -240,7 +241,7 @@ struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st,
 	}
 	graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0);
 	close(fd);
-	ret = parse_commit_graph(graph_map, graph_size);
+	ret = parse_commit_graph(r, graph_map, graph_size);
 
 	if (ret)
 		ret->odb = odb;
@@ -280,7 +281,8 @@ static int verify_commit_graph_lite(struct commit_graph *g)
 	return 0;
 }
 
-struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
+struct commit_graph *parse_commit_graph(struct repository *r,
+					void *graph_map, size_t graph_size)
 {
 	const unsigned char *data, *chunk_lookup;
 	uint32_t i;
@@ -445,7 +447,8 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
 	return NULL;
 }
 
-static struct commit_graph *load_commit_graph_one(const char *graph_file,
+static struct commit_graph *load_commit_graph_one(struct repository *r,
+						  const char *graph_file,
 						  struct object_directory *odb)
 {
 
@@ -457,7 +460,7 @@ static struct commit_graph *load_commit_graph_one(const char *graph_file,
 	if (!open_ok)
 		return NULL;
 
-	g = load_commit_graph_one_fd_st(fd, &st, odb);
+	g = load_commit_graph_one_fd_st(r, fd, &st, odb);
 
 	if (g)
 		g->filename = xstrdup(graph_file);
@@ -469,7 +472,7 @@ static struct commit_graph *load_commit_graph_v1(struct repository *r,
 						 struct object_directory *odb)
 {
 	char *graph_name = get_commit_graph_filename(odb);
-	struct commit_graph *g = load_commit_graph_one(graph_name, odb);
+	struct commit_graph *g = load_commit_graph_one(r, graph_name, odb);
 	free(graph_name);
 
 	return g;
@@ -550,7 +553,7 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r,
 		valid = 0;
 		for (odb = r->objects->odb; odb; odb = odb->next) {
 			char *graph_name = get_split_graph_filename(odb, line.buf);
-			struct commit_graph *g = load_commit_graph_one(graph_name, odb);
+			struct commit_graph *g = load_commit_graph_one(r, graph_name, odb);
 
 			free(graph_name);
 
diff --git a/commit-graph.h b/commit-graph.h
index 0677dd1031..d9acb22bac 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -75,11 +75,13 @@ struct commit_graph {
 	struct bloom_filter_settings *bloom_filter_settings;
 };
 
-struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st,
+struct commit_graph *load_commit_graph_one_fd_st(struct repository *r,
+						 int fd, struct stat *st,
 						 struct object_directory *odb);
 struct commit_graph *read_commit_graph_one(struct repository *r,
 					   struct object_directory *odb);
-struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size);
+struct commit_graph *parse_commit_graph(struct repository *r,
+					void *graph_map, size_t graph_size);
 
 /*
  * Return 1 if and only if the repository has a commit-graph
diff --git a/fuzz-commit-graph.c b/fuzz-commit-graph.c
index 430817214d..e7cf6d5b0f 100644
--- a/fuzz-commit-graph.c
+++ b/fuzz-commit-graph.c
@@ -1,7 +1,8 @@
 #include "commit-graph.h"
 #include "repository.h"
 
-struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size);
+struct commit_graph *parse_commit_graph(struct repository *r,
+					void *graph_map, size_t graph_size);
 
 int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size);
 
@@ -10,7 +11,7 @@ int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size)
 	struct commit_graph *g;
 
 	initialize_the_repository();
-	g = parse_commit_graph((void *)data, size);
+	g = parse_commit_graph(the_repository, (void *)data, size);
 	repo_clear(the_repository);
 	free_commit_graph(g);
 

bloom.h, commit-graph.c, t/t4216-log-bloom.sh

diff --git a/bloom.h b/bloom.h
index d8fbb0fbf1..0b9b59a6fe 100644
--- a/bloom.h
+++ b/bloom.h
@@ -28,9 +28,18 @@ struct bloom_filter_settings {
 	 * that contain n*b bits.
 	 */
 	uint32_t bits_per_entry;
+
+	/*
+	 * The maximum number of changed paths per commit
+	 * before declaring a Bloom filter to be too-large.
+	 *
+	 * Not written to the commit-graph file.
+	 */
+	uint32_t max_changed_paths;
 };
 
-#define DEFAULT_BLOOM_FILTER_SETTINGS { 1, 7, 10 }
+#define DEFAULT_BLOOM_MAX_CHANGES 512
+#define DEFAULT_BLOOM_FILTER_SETTINGS { 1, 7, 10, DEFAULT_BLOOM_MAX_CHANGES }
 #define BITS_PER_WORD 8
 #define BLOOMDATA_CHUNK_HEADER_SIZE 3 * sizeof(uint32_t)
 
diff --git a/commit-graph.c b/commit-graph.c
index a516e93d71..86dd4b979e 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1194,6 +1194,7 @@ static void trace2_bloom_filter_settings(struct write_commit_graph_context *ctx)
 	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_object_intmax(&jw, "max_changed_paths", ctx->bloom_settings->max_changed_paths);
 	jw_end(&jw);
 
 	trace2_data_json("bloom", ctx->r, "settings", &jw);
@@ -1662,6 +1663,8 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 							      bloom_settings.bits_per_entry);
 		bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES",
 							  bloom_settings.num_hashes);
+		bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS",
+							  bloom_settings.max_changed_paths);
 		ctx->bloom_settings = &bloom_settings;
 	}
 
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index b3d1f596f8..eb2bcc51f0 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -169,11 +169,11 @@ test_expect_success 'persist filter settings' '
 		GIT_TEST_BLOOM_SETTINGS_NUM_HASHES=9 \
 		GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY=15 \
 		git commit-graph write --reachable --changed-paths &&
-	grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15}" trace2.txt &&
+	grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15" trace2.txt &&
 	GIT_TRACE2_EVENT="$(pwd)/trace2-auto.txt" \
 		GIT_TRACE2_EVENT_NESTING=5 \
 		git commit-graph write --reachable --changed-paths &&
-	grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15}" trace2-auto.txt
+	grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15" trace2-auto.txt
 '
 
 test_expect_success 'correctly report changes over limit' '

diff --git a/t/helper/test-read-graph.c b/t/helper/test-read-graph.c
index 6d0c962438..5f585a1725 100644
--- a/t/helper/test-read-graph.c
+++ b/t/helper/test-read-graph.c
@@ -12,11 +12,12 @@ int cmd__read_graph(int argc, const char **argv)
 	setup_git_directory();
 	odb = the_repository->objects->odb;
 
+	prepare_repo_settings(the_repository);
+
 	graph = read_commit_graph_one(the_repository, odb);
 	if (!graph)
 		return 1;
 
-
 	printf("header: %08x %d %d %d %d\n",
 		ntohl(*(uint32_t*)graph->data),
 		*(unsigned char*)(graph->data + 4),

Documentation/config.txt, Documentation/config/commitgraph.txt, commit-graph.c, repo-settings.c, repository.h, t/t4216-log-bloom.sh

diff --git a/Documentation/config.txt b/Documentation/config.txt
index ef0768b91a..78883c6e63 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -340,6 +340,8 @@ include::config/column.txt[]
 
 include::config/commit.txt[]
 
+include::config/commitgraph.txt[]
+
 include::config/credential.txt[]
 
 include::config/completion.txt[]
diff --git a/Documentation/config/commitgraph.txt b/Documentation/config/commitgraph.txt
new file mode 100644
index 0000000000..cff0797b54
--- /dev/null
+++ b/Documentation/config/commitgraph.txt
@@ -0,0 +1,4 @@
+commitGraph.readChangedPaths::
+	If true, then git will use the changed-path Bloom filters in the
+	commit-graph file (if it exists, and they are present). Defaults to
+	true. See linkgit:git-commit-graph[1] for more information.
diff --git a/commit-graph.c b/commit-graph.c
index 0c1030641c..a516e93d71 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -320,6 +320,8 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 		return NULL;
 	}
 
+	prepare_repo_settings(r);
+
 	graph = alloc_commit_graph();
 
 	graph->hash_len = the_hash_algo->rawsz;
@@ -396,14 +398,14 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 		case GRAPH_CHUNKID_BLOOMINDEXES:
 			if (graph->chunk_bloom_indexes)
 				chunk_repeated = 1;
-			else
+			else if (r->settings.commit_graph_read_changed_paths)
 				graph->chunk_bloom_indexes = data + chunk_offset;
 			break;
 
 		case GRAPH_CHUNKID_BLOOMDATA:
 			if (graph->chunk_bloom_data)
 				chunk_repeated = 1;
-			else {
+			else if (r->settings.commit_graph_read_changed_paths) {
 				uint32_t hash_version;
 				graph->chunk_bloom_data = data + chunk_offset;
 				hash_version = get_be32(data + chunk_offset);
diff --git a/repo-settings.c b/repo-settings.c
index 0918408b34..9e551bc03d 100644
--- a/repo-settings.c
+++ b/repo-settings.c
@@ -17,9 +17,12 @@ void prepare_repo_settings(struct repository *r)
 
 	if (!repo_config_get_bool(r, "core.commitgraph", &value))
 		r->settings.core_commit_graph = value;
+	if (!repo_config_get_bool(r, "commitgraph.readchangedpaths", &value))
+		r->settings.commit_graph_read_changed_paths = value;
 	if (!repo_config_get_bool(r, "gc.writecommitgraph", &value))
 		r->settings.gc_write_commit_graph = value;
 	UPDATE_DEFAULT_BOOL(r->settings.core_commit_graph, 1);
+	UPDATE_DEFAULT_BOOL(r->settings.commit_graph_read_changed_paths, 1);
 	UPDATE_DEFAULT_BOOL(r->settings.gc_write_commit_graph, 1);
 
 	if (!repo_config_get_int(r, "index.version", &value))
diff --git a/repository.h b/repository.h
index 3c1f7d54bd..81759b7d27 100644
--- a/repository.h
+++ b/repository.h
@@ -29,6 +29,7 @@ struct repo_settings {
 	int initialized;
 
 	int core_commit_graph;
+	int commit_graph_read_changed_paths;
 	int gc_write_commit_graph;
 	int fetch_write_commit_graph;
 
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index fe19f6a60c..b3d1f596f8 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -90,7 +90,9 @@ do
 		      "--ancestry-path side..master"
 	do
 		test_expect_success "git log option: $option for path: $path" '
-			test_bloom_filters_used "$option -- $path"
+			test_bloom_filters_used "$option -- $path" &&
+			test_config commitgraph.readChangedPaths false &&
+			test_bloom_filters_not_used "$option -- $path"
 		'
 	done
 done

Documentation/config/commitgraph.txt, Documentation/git-commit-graph.txt, bloom.c, builtin/commit-graph.c, commit-graph.c, commit-graph.h, t/t4216-log-bloom.sh

diff --git a/Documentation/config/commitgraph.txt b/Documentation/config/commitgraph.txt
index cff0797b54..4582c39fc4 100644
--- a/Documentation/config/commitgraph.txt
+++ b/Documentation/config/commitgraph.txt
@@ -1,3 +1,7 @@
+commitGraph.maxNewFilters::
+	Specifies the default value for the `--max-new-filters` option of `git
+	commit-graph write` (c.f., linkgit:git-commit-graph[1]).
+
 commitGraph.readChangedPaths::
 	If true, then git will use the changed-path Bloom filters in the
 	commit-graph file (if it exists, and they are present). Defaults to
diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt
index 17405c73a9..9c887d5d79 100644
--- a/Documentation/git-commit-graph.txt
+++ b/Documentation/git-commit-graph.txt
@@ -67,6 +67,10 @@ this option is given, future commit-graph writes will automatically assume
 that this option was intended. Use `--no-changed-paths` to stop storing this
 data.
 +
+With the `--max-new-filters=<n>` option, generate at most `n` new Bloom
+filters (if `--changed-paths` is specified). If `n` is `-1`, no limit is
+enforced. Overrides the `commitGraph.maxNewFilters` configuration.
++
 With the `--split[=<strategy>]` option, write the commit-graph as a
 chain of multiple commit-graph files stored in
 `<dir>/info/commit-graphs`. Commit-graph layers are merged based on the
diff --git a/bloom.c b/bloom.c
index ed54e96e57..d0c0fd049d 100644
--- a/bloom.c
+++ b/bloom.c
@@ -51,6 +51,21 @@ static int load_bloom_filter_from_graph(struct commit_graph *g,
 	else
 		start_index = 0;
 
+	if ((start_index == end_index) &&
+	    (g->bloom_large.word_alloc && !bitmap_get(&g->bloom_large, lex_pos))) {
+		/*
+		 * If the filter is zero-length, either (1) the filter has no
+		 * changes, (2) the filter has too many changes, or (3) it
+		 * wasn't computed (eg., due to '--max-new-filters').
+		 *
+		 * If either (1) or (2) is the case, the 'large' bit will be set
+		 * for this Bloom filter. If it is unset, then it wasn't
+		 * computed. In that case, return nothing, since we don't have
+		 * that filter in the graph.
+		 */
+		return 0;
+	}
+
 	filter->len = end_index - start_index;
 	filter->data = (unsigned char *)(g->chunk_bloom_data +
 					sizeof(unsigned char) * start_index +
diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index 38f5f57d15..3500a6e1f1 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -13,7 +13,8 @@ static char const * const builtin_commit_graph_usage[] = {
 	N_("git commit-graph verify [--object-dir <objdir>] [--shallow] [--[no-]progress]"),
 	N_("git commit-graph write [--object-dir <objdir>] [--append] "
 	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
-	   "[--changed-paths] [--[no-]progress] <split options>"),
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
@@ -25,7 +26,8 @@ static const char * const builtin_commit_graph_verify_usage[] = {
 static const char * const builtin_commit_graph_write_usage[] = {
 	N_("git commit-graph write [--object-dir <objdir>] [--append] "
 	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
-	   "[--changed-paths] [--[no-]progress] <split options>"),
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
@@ -162,6 +164,23 @@ static int read_one_commit(struct oidset *commits, struct progress *progress,
 	return 0;
 }
 
+static int write_option_max_new_filters(const struct option *opt,
+					const char *arg,
+					int unset)
+{
+	int *to = opt->value;
+	if (unset)
+		*to = -1;
+	else {
+		const char *s;
+		*to = strtol(arg, (char **)&s, 10);
+		if (*s)
+			return error(_("%s expects a numerical value"),
+				     optname(opt, opt->flags));
+	}
+	return 0;
+}
+
 static int graph_write(int argc, const char **argv)
 {
 	struct string_list pack_indexes = STRING_LIST_INIT_NODUP;
@@ -197,6 +216,9 @@ static int graph_write(int argc, const char **argv)
 			N_("maximum ratio between two levels of a split commit-graph")),
 		OPT_EXPIRY_DATE(0, "expire-time", &write_opts.expire_time,
 			N_("only expire files older than a given date-time")),
+		OPT_CALLBACK_F(0, "max-new-filters", &write_opts.max_new_filters,
+			NULL, N_("maximum number of changed-path Bloom filters to compute"),
+			0, write_option_max_new_filters),
 		OPT_END(),
 	};
 
@@ -205,6 +227,7 @@ static int graph_write(int argc, const char **argv)
 	write_opts.size_multiple = 2;
 	write_opts.max_commits = 0;
 	write_opts.expire_time = 0;
+	write_opts.max_new_filters = -1;
 
 	trace2_cmd_mode("write");
 
@@ -270,6 +293,16 @@ static int graph_write(int argc, const char **argv)
 	return result;
 }
 
+static int git_commit_graph_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "commitgraph.maxnewfilters")) {
+		write_opts.max_new_filters = git_config_int(var, value);
+		return 0;
+	}
+
+	return git_default_config(var, value, cb);
+}
+
 int cmd_commit_graph(int argc, const char **argv, const char *prefix)
 {
 	static struct option builtin_commit_graph_options[] = {
@@ -283,7 +316,7 @@ int cmd_commit_graph(int argc, const char **argv, const char *prefix)
 		usage_with_options(builtin_commit_graph_usage,
 				   builtin_commit_graph_options);
 
-	git_config(git_default_config, NULL);
+	git_config(git_commit_graph_config, &opts);
 	argc = parse_options(argc, argv, prefix,
 			     builtin_commit_graph_options,
 			     builtin_commit_graph_usage,
diff --git a/commit-graph.c b/commit-graph.c
index 82fca07579..76b1238262 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -948,7 +948,8 @@ struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit
 }
 
 static int get_bloom_filter_large_in_graph(struct commit_graph *g,
-					   const struct commit *c)
+					   const struct commit *c,
+					   uint32_t max_changed_paths)
 {
 	uint32_t graph_pos = commit_graph_position(c);
 	if (graph_pos == COMMIT_NOT_FROM_GRAPH)
@@ -1475,6 +1476,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 	int i;
 	struct progress *progress = NULL;
 	int *sorted_commits;
+	int max_new_filters;
 
 	init_bloom_filters();
 	ctx->bloom_large = bitmap_word_alloc(ctx->commits.nr / BITS_IN_EWORD + 1);
@@ -1491,10 +1493,15 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 		ctx->order_by_pack ? commit_pos_cmp : commit_gen_cmp,
 		&ctx->commits);
 
+	max_new_filters = ctx->opts->max_new_filters >= 0 ?
+		ctx->opts->max_new_filters : ctx->commits.nr;
+
 	for (i = 0; i < ctx->commits.nr; i++) {
 		int pos = sorted_commits[i];
 		struct commit *c = ctx->commits.list[pos];
-		if (get_bloom_filter_large_in_graph(ctx->r->objects->commit_graph, c)) {
+		if (get_bloom_filter_large_in_graph(ctx->r->objects->commit_graph,
+						    c,
+						    ctx->bloom_settings->max_changed_paths)) {
 			bitmap_set(ctx->bloom_large, pos);
 			ctx->count_bloom_filter_known_large++;
 		} else {
@@ -1502,7 +1509,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 			struct bloom_filter *filter = get_or_compute_bloom_filter(
 				ctx->r,
 				c,
-				1,
+				ctx->count_bloom_filter_computed < max_new_filters,
 				ctx->bloom_settings,
 				&computed);
 			if (computed) {
@@ -1512,7 +1519,8 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 					ctx->count_bloom_filter_found_large++;
 				}
 			}
-			ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
+			if (filter)
+				ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
 		}
 		display_progress(progress, i + 1);
 	}
diff --git a/commit-graph.h b/commit-graph.h
index 1d147b7b76..47d99ea4bf 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -115,6 +115,7 @@ struct commit_graph_opts {
 	int max_commits;
 	timestamp_t expire_time;
 	enum commit_graph_split_flags flags;
+	int max_new_filters;
 };
 
 /*
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index 6859d85369..3aab8ffbe3 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -286,4 +286,23 @@ test_expect_success 'Bloom generation does not recompute too-large filters' '
 	)
 '
 
+test_expect_success 'Bloom generation is limited by --max-new-filters' '
+	(
+		cd limits &&
+		test_commit c2 filter &&
+		test_commit c3 filter &&
+		test_commit c4 no-filter &&
+		test_bloom_filters_computed "--reachable --changed-paths --split=replace --max-new-filters=2" \
+			2 0 2
+	)
+'
+
+test_expect_success 'Bloom generation backfills previously-skipped filters' '
+	(
+		cd limits &&
+		test_bloom_filters_computed "--reachable --changed-paths --split=replace --max-new-filters=1" \
+			2 0 1
+	)
+'
+
 test_done

blame.c, bloom.c, commit-graph.c, commit-graph.h, revision.c, t/t4216-log-bloom.sh, t/t5324-split-commit-graph.sh

diff --git a/blame.c b/blame.c
index 82fa16d658..3e5f8787bc 100644
--- a/blame.c
+++ b/blame.c
@@ -2891,16 +2891,18 @@ void setup_blame_bloom_data(struct blame_scoreboard *sb,
 			    const char *path)
 {
 	struct blame_bloom_data *bd;
+	struct bloom_filter_settings *bs;
 
 	if (!sb->repo->objects->commit_graph)
 		return;
 
-	if (!sb->repo->objects->commit_graph->bloom_filter_settings)
+	bs = get_bloom_filter_settings(sb->repo);
+	if (!bs)
 		return;
 
 	bd = xmalloc(sizeof(struct blame_bloom_data));
 
-	bd->settings = sb->repo->objects->commit_graph->bloom_filter_settings;
+	bd->settings = bs;
 
 	bd->alloc = 4;
 	bd->nr = 0;
diff --git a/bloom.c b/bloom.c
index 1a573226e7..cd9380ac62 100644
--- a/bloom.c
+++ b/bloom.c
@@ -38,7 +38,7 @@ static int load_bloom_filter_from_graph(struct commit_graph *g,
 	while (graph_pos < g->num_commits_in_base)
 		g = g->base_graph;
 
-	/* The commit graph commit 'c' lives in doesn't carry bloom filters. */
+	/* The commit graph commit 'c' lives in doesn't carry Bloom filters. */
 	if (!g->chunk_bloom_indexes)
 		return 0;
 
@@ -195,8 +195,8 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 	if (!filter->data) {
 		load_commit_graph_info(r, c);
 		if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH &&
-			r->objects->commit_graph->chunk_bloom_indexes)
-			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c);
+			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c))
+				return filter;
 	}
 
 	if (filter->data)
diff --git a/commit-graph.c b/commit-graph.c
index e51c91dd5b..d4b06811be 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -660,6 +660,17 @@ int generation_numbers_enabled(struct repository *r)
 	return !!first_generation;
 }
 
+struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r)
+{
+	struct commit_graph *g = r->objects->commit_graph;
+	while (g) {
+		if (g->bloom_filter_settings)
+			return g->bloom_filter_settings;
+		g = g->base_graph;
+	}
+	return NULL;
+}
+
 static void close_commit_graph_one(struct commit_graph *g)
 {
 	if (!g)
diff --git a/commit-graph.h b/commit-graph.h
index 09a97030dc..0677dd1031 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -87,6 +87,8 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size);
  */
 int generation_numbers_enabled(struct repository *r);
 
+struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r);
+
 enum commit_graph_write_flags {
 	COMMIT_GRAPH_WRITE_APPEND     = (1 << 0),
 	COMMIT_GRAPH_WRITE_PROGRESS   = (1 << 1),
diff --git a/revision.c b/revision.c
index 3dcf689341..be600186ee 100644
--- a/revision.c
+++ b/revision.c
@@ -680,10 +680,7 @@ static void prepare_to_use_bloom_filter(struct rev_info *revs)
 
 	repo_parse_commit(revs->repo, revs->commits->item);
 
-	if (!revs->repo->objects->commit_graph)
-		return;
-
-	revs->bloom_filter_settings = revs->repo->objects->commit_graph->bloom_filter_settings;
+	revs->bloom_filter_settings = get_bloom_filter_settings(revs->repo);
 	if (!revs->bloom_filter_settings)
 		return;
 
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index c21cc160f3..c9f9bdf1ba 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -60,7 +60,7 @@ setup () {
 
 test_bloom_filters_used () {
 	log_args=$1
-	bloom_trace_prefix="statistics:{\"filter_not_present\":0,\"maybe\""
+	bloom_trace_prefix="statistics:{\"filter_not_present\":${2:-0},\"maybe\""
 	setup "$log_args" &&
 	grep -q "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.perf" &&
 	test_cmp log_wo_bloom log_w_bloom &&
@@ -134,8 +134,11 @@ test_expect_success 'setup - add commit-graph to the chain without Bloom filters
 	test_line_count = 2 .git/objects/info/commit-graphs/commit-graph-chain
 '
 
-test_expect_success 'Do not use Bloom filters if the latest graph does not have Bloom filters.' '
-	test_bloom_filters_not_used "-- A/B"
+test_expect_success 'use Bloom filters even if the latest graph does not have Bloom filters' '
+	# Ensure that the number of empty filters is equal to the number of
+	# filters in the latest graph layer to prove that they are loaded (and
+	# ignored).
+	test_bloom_filters_used "-- A/B" 3
 '
 
 test_expect_success 'setup - add commit-graph to the chain with Bloom filters' '
diff --git a/t/t5324-split-commit-graph.sh b/t/t5324-split-commit-graph.sh
index 9b850ea907..5bdfd53ef9 100755
--- a/t/t5324-split-commit-graph.sh
+++ b/t/t5324-split-commit-graph.sh
@@ -425,4 +425,17 @@ done <<\EOF
 0600 -r--------
 EOF
 
+test_expect_success '--split=replace with partial Bloom data' '
+	rm -rf $graphdir $infodir/commit-graph &&
+	git reset --hard commits/3 &&
+	git rev-list -1 HEAD~2 >a &&
+	git rev-list -1 HEAD~1 >b &&
+	git commit-graph write --split=no-merge --stdin-commits --changed-paths <a &&
+	git commit-graph write --split=no-merge --stdin-commits <b &&
+	git commit-graph write --split=replace --stdin-commits --changed-paths <c &&
+	ls $graphdir/graph-*.graph >graph-files &&
+	test_line_count = 1 graph-files &&
+	verify_chain_files_exist $graphdir
+'
+
 test_done

diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index c9f9bdf1ba..fe19f6a60c 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -53,7 +53,7 @@ sane_unset GIT_TRACE2_PERF_BRIEF
 sane_unset GIT_TRACE2_CONFIG_PARAMS
 
 setup () {
-	rm "$TRASH_DIRECTORY/trace.perf"
+	rm -f "$TRASH_DIRECTORY/trace.perf" &&
 	git -c core.commitGraph=false log --pretty="format:%s" $1 >log_wo_bloom &&
 	GIT_TRACE2_PERF="$TRASH_DIRECTORY/trace.perf" git -c core.commitGraph=true log --pretty="format:%s" $1 >log_w_bloom
 }

builtin/commit-graph.c, commit-graph.c, commit-graph.h, fuzz-commit-graph.c

diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index 523501f217..ba5584463f 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -106,7 +106,7 @@ static int graph_verify(int argc, const char **argv)
 	FREE_AND_NULL(graph_name);
 
 	if (open_ok)
-		graph = load_commit_graph_one_fd_st(fd, &st, odb);
+		graph = load_commit_graph_one_fd_st(the_repository, fd, &st, odb);
 	else
 		graph = read_commit_graph_one(the_repository, odb);
 
diff --git a/commit-graph.c b/commit-graph.c
index d4b06811be..0c1030641c 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -224,7 +224,8 @@ int open_commit_graph(const char *graph_file, int *fd, struct stat *st)
 	return 1;
 }
 
-struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st,
+struct commit_graph *load_commit_graph_one_fd_st(struct repository *r,
+						 int fd, struct stat *st,
 						 struct object_directory *odb)
 {
 	void *graph_map;
@@ -240,7 +241,7 @@ struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st,
 	}
 	graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0);
 	close(fd);
-	ret = parse_commit_graph(graph_map, graph_size);
+	ret = parse_commit_graph(r, graph_map, graph_size);
 
 	if (ret)
 		ret->odb = odb;
@@ -280,7 +281,8 @@ static int verify_commit_graph_lite(struct commit_graph *g)
 	return 0;
 }
 
-struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
+struct commit_graph *parse_commit_graph(struct repository *r,
+					void *graph_map, size_t graph_size)
 {
 	const unsigned char *data, *chunk_lookup;
 	uint32_t i;
@@ -445,7 +447,8 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
 	return NULL;
 }
 
-static struct commit_graph *load_commit_graph_one(const char *graph_file,
+static struct commit_graph *load_commit_graph_one(struct repository *r,
+						  const char *graph_file,
 						  struct object_directory *odb)
 {
 
@@ -457,7 +460,7 @@ static struct commit_graph *load_commit_graph_one(const char *graph_file,
 	if (!open_ok)
 		return NULL;
 
-	g = load_commit_graph_one_fd_st(fd, &st, odb);
+	g = load_commit_graph_one_fd_st(r, fd, &st, odb);
 
 	if (g)
 		g->filename = xstrdup(graph_file);
@@ -469,7 +472,7 @@ static struct commit_graph *load_commit_graph_v1(struct repository *r,
 						 struct object_directory *odb)
 {
 	char *graph_name = get_commit_graph_filename(odb);
-	struct commit_graph *g = load_commit_graph_one(graph_name, odb);
+	struct commit_graph *g = load_commit_graph_one(r, graph_name, odb);
 	free(graph_name);
 
 	return g;
@@ -550,7 +553,7 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r,
 		valid = 0;
 		for (odb = r->objects->odb; odb; odb = odb->next) {
 			char *graph_name = get_split_graph_filename(odb, line.buf);
-			struct commit_graph *g = load_commit_graph_one(graph_name, odb);
+			struct commit_graph *g = load_commit_graph_one(r, graph_name, odb);
 
 			free(graph_name);
 
diff --git a/commit-graph.h b/commit-graph.h
index 0677dd1031..d9acb22bac 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -75,11 +75,13 @@ struct commit_graph {
 	struct bloom_filter_settings *bloom_filter_settings;
 };
 
-struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st,
+struct commit_graph *load_commit_graph_one_fd_st(struct repository *r,
+						 int fd, struct stat *st,
 						 struct object_directory *odb);
 struct commit_graph *read_commit_graph_one(struct repository *r,
 					   struct object_directory *odb);
-struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size);
+struct commit_graph *parse_commit_graph(struct repository *r,
+					void *graph_map, size_t graph_size);
 
 /*
  * Return 1 if and only if the repository has a commit-graph
diff --git a/fuzz-commit-graph.c b/fuzz-commit-graph.c
index 430817214d..e7cf6d5b0f 100644
--- a/fuzz-commit-graph.c
+++ b/fuzz-commit-graph.c
@@ -1,7 +1,8 @@
 #include "commit-graph.h"
 #include "repository.h"
 
-struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size);
+struct commit_graph *parse_commit_graph(struct repository *r,
+					void *graph_map, size_t graph_size);
 
 int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size);
 
@@ -10,7 +11,7 @@ int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size)
 	struct commit_graph *g;
 
 	initialize_the_repository();
-	g = parse_commit_graph((void *)data, size);
+	g = parse_commit_graph(the_repository, (void *)data, size);
 	repo_clear(the_repository);
 	free_commit_graph(g);
 

diff --git a/t/helper/test-read-graph.c b/t/helper/test-read-graph.c
index 6d0c962438..5f585a1725 100644
--- a/t/helper/test-read-graph.c
+++ b/t/helper/test-read-graph.c
@@ -12,11 +12,12 @@ int cmd__read_graph(int argc, const char **argv)
 	setup_git_directory();
 	odb = the_repository->objects->odb;
 
+	prepare_repo_settings(the_repository);
+
 	graph = read_commit_graph_one(the_repository, odb);
 	if (!graph)
 		return 1;
 
-
 	printf("header: %08x %d %d %d %d\n",
 		ntohl(*(uint32_t*)graph->data),
 		*(unsigned char*)(graph->data + 4),

Documentation/config.txt, Documentation/config/commitgraph.txt, commit-graph.c, repo-settings.c, repository.h, t/t4216-log-bloom.sh

diff --git a/Documentation/config.txt b/Documentation/config.txt
index ef0768b91a..78883c6e63 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -340,6 +340,8 @@ include::config/column.txt[]
 
 include::config/commit.txt[]
 
+include::config/commitgraph.txt[]
+
 include::config/credential.txt[]
 
 include::config/completion.txt[]
diff --git a/Documentation/config/commitgraph.txt b/Documentation/config/commitgraph.txt
new file mode 100644
index 0000000000..cff0797b54
--- /dev/null
+++ b/Documentation/config/commitgraph.txt
@@ -0,0 +1,4 @@
+commitGraph.readChangedPaths::
+	If true, then git will use the changed-path Bloom filters in the
+	commit-graph file (if it exists, and they are present). Defaults to
+	true. See linkgit:git-commit-graph[1] for more information.
diff --git a/commit-graph.c b/commit-graph.c
index 0c1030641c..a516e93d71 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -320,6 +320,8 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 		return NULL;
 	}
 
+	prepare_repo_settings(r);
+
 	graph = alloc_commit_graph();
 
 	graph->hash_len = the_hash_algo->rawsz;
@@ -396,14 +398,14 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 		case GRAPH_CHUNKID_BLOOMINDEXES:
 			if (graph->chunk_bloom_indexes)
 				chunk_repeated = 1;
-			else
+			else if (r->settings.commit_graph_read_changed_paths)
 				graph->chunk_bloom_indexes = data + chunk_offset;
 			break;
 
 		case GRAPH_CHUNKID_BLOOMDATA:
 			if (graph->chunk_bloom_data)
 				chunk_repeated = 1;
-			else {
+			else if (r->settings.commit_graph_read_changed_paths) {
 				uint32_t hash_version;
 				graph->chunk_bloom_data = data + chunk_offset;
 				hash_version = get_be32(data + chunk_offset);
diff --git a/repo-settings.c b/repo-settings.c
index 0918408b34..9e551bc03d 100644
--- a/repo-settings.c
+++ b/repo-settings.c
@@ -17,9 +17,12 @@ void prepare_repo_settings(struct repository *r)
 
 	if (!repo_config_get_bool(r, "core.commitgraph", &value))
 		r->settings.core_commit_graph = value;
+	if (!repo_config_get_bool(r, "commitgraph.readchangedpaths", &value))
+		r->settings.commit_graph_read_changed_paths = value;
 	if (!repo_config_get_bool(r, "gc.writecommitgraph", &value))
 		r->settings.gc_write_commit_graph = value;
 	UPDATE_DEFAULT_BOOL(r->settings.core_commit_graph, 1);
+	UPDATE_DEFAULT_BOOL(r->settings.commit_graph_read_changed_paths, 1);
 	UPDATE_DEFAULT_BOOL(r->settings.gc_write_commit_graph, 1);
 
 	if (!repo_config_get_int(r, "index.version", &value))
diff --git a/repository.h b/repository.h
index 3c1f7d54bd..81759b7d27 100644
--- a/repository.h
+++ b/repository.h
@@ -29,6 +29,7 @@ struct repo_settings {
 	int initialized;
 
 	int core_commit_graph;
+	int commit_graph_read_changed_paths;
 	int gc_write_commit_graph;
 	int fetch_write_commit_graph;
 
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index fe19f6a60c..b3d1f596f8 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -90,7 +90,9 @@ do
 		      "--ancestry-path side..master"
 	do
 		test_expect_success "git log option: $option for path: $path" '
-			test_bloom_filters_used "$option -- $path"
+			test_bloom_filters_used "$option -- $path" &&
+			test_config commitgraph.readChangedPaths false &&
+			test_bloom_filters_not_used "$option -- $path"
 		'
 	done
 done

bloom.h, commit-graph.c, t/t4216-log-bloom.sh

diff --git a/bloom.h b/bloom.h
index d8fbb0fbf1..0b9b59a6fe 100644
--- a/bloom.h
+++ b/bloom.h
@@ -28,9 +28,18 @@ struct bloom_filter_settings {
 	 * that contain n*b bits.
 	 */
 	uint32_t bits_per_entry;
+
+	/*
+	 * The maximum number of changed paths per commit
+	 * before declaring a Bloom filter to be too-large.
+	 *
+	 * Not written to the commit-graph file.
+	 */
+	uint32_t max_changed_paths;
 };
 
-#define DEFAULT_BLOOM_FILTER_SETTINGS { 1, 7, 10 }
+#define DEFAULT_BLOOM_MAX_CHANGES 512
+#define DEFAULT_BLOOM_FILTER_SETTINGS { 1, 7, 10, DEFAULT_BLOOM_MAX_CHANGES }
 #define BITS_PER_WORD 8
 #define BLOOMDATA_CHUNK_HEADER_SIZE 3 * sizeof(uint32_t)
 
diff --git a/commit-graph.c b/commit-graph.c
index a516e93d71..86dd4b979e 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1194,6 +1194,7 @@ static void trace2_bloom_filter_settings(struct write_commit_graph_context *ctx)
 	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_object_intmax(&jw, "max_changed_paths", ctx->bloom_settings->max_changed_paths);
 	jw_end(&jw);
 
 	trace2_data_json("bloom", ctx->r, "settings", &jw);
@@ -1662,6 +1663,8 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 							      bloom_settings.bits_per_entry);
 		bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES",
 							  bloom_settings.num_hashes);
+		bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS",
+							  bloom_settings.max_changed_paths);
 		ctx->bloom_settings = &bloom_settings;
 	}
 
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index b3d1f596f8..eb2bcc51f0 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -169,11 +169,11 @@ test_expect_success 'persist filter settings' '
 		GIT_TEST_BLOOM_SETTINGS_NUM_HASHES=9 \
 		GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY=15 \
 		git commit-graph write --reachable --changed-paths &&
-	grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15}" trace2.txt &&
+	grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15" trace2.txt &&
 	GIT_TRACE2_EVENT="$(pwd)/trace2-auto.txt" \
 		GIT_TRACE2_EVENT_NESTING=5 \
 		git commit-graph write --reachable --changed-paths &&
-	grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15}" trace2-auto.txt
+	grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15" trace2-auto.txt
 '
 
 test_expect_success 'correctly report changes over limit' '

blame.c, bloom.c, bloom.h, commit-graph.c, line-log.c, revision.c, t/helper/test-bloom.c

diff --git a/blame.c b/blame.c
index 3e5f8787bc..756285fca7 100644
--- a/blame.c
+++ b/blame.c
@@ -1275,7 +1275,7 @@ static int maybe_changed_path(struct repository *r,
 	if (commit_graph_generation(origin->commit) == GENERATION_NUMBER_INFINITY)
 		return 1;
 
-	filter = get_bloom_filter(r, origin->commit, 0);
+	filter = get_bloom_filter(r, origin->commit);
 
 	if (!filter)
 		return 1;
diff --git a/bloom.c b/bloom.c
index cd9380ac62..a8a21762f4 100644
--- a/bloom.c
+++ b/bloom.c
@@ -177,9 +177,10 @@ static int pathmap_cmp(const void *hashmap_cmp_fn_data,
 	return strcmp(e1->path, e2->path);
 }
 
-struct bloom_filter *get_bloom_filter(struct repository *r,
-				      struct commit *c,
-				      int compute_if_not_present)
+struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
+						 struct commit *c,
+						 int compute_if_not_present,
+						 int *computed)
 {
 	struct bloom_filter *filter;
 	struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
@@ -187,6 +188,9 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 	struct diff_options diffopt;
 	int max_changes = 512;
 
+	if (computed)
+		*computed = 0;
+
 	if (!bloom_filters.slab_size)
 		return NULL;
 
@@ -273,6 +277,9 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 		filter->len = 0;
 	}
 
+	if (computed)
+		*computed = 1;
+
 	free(diff_queued_diff.queue);
 	DIFF_QUEUE_CLEAR(&diff_queued_diff);
 
diff --git a/bloom.h b/bloom.h
index 0b9b59a6fe..baa91926db 100644
--- a/bloom.h
+++ b/bloom.h
@@ -89,9 +89,13 @@ void add_key_to_filter(const struct bloom_key *key,
 
 void init_bloom_filters(void);
 
-struct bloom_filter *get_bloom_filter(struct repository *r,
-				      struct commit *c,
-				      int compute_if_not_present);
+struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
+						 struct commit *c,
+						 int compute_if_not_present,
+						 int *computed);
+
+#define get_bloom_filter(r, c) get_or_compute_bloom_filter( \
+	(r), (c), 0, NULL)
 
 int bloom_filter_contains(const struct bloom_filter *filter,
 			  const struct bloom_key *key,
diff --git a/commit-graph.c b/commit-graph.c
index 86dd4b979e..ba2a2cfb22 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -964,6 +964,9 @@ struct write_commit_graph_context {
 	const struct split_commit_graph_opts *split_opts;
 	size_t total_bloom_filter_data_size;
 	const struct bloom_filter_settings *bloom_settings;
+
+	int count_bloom_filter_found_large;
+	int count_bloom_filter_computed;
 };
 
 static int write_graph_chunk_fanout(struct hashfile *f,
@@ -1175,7 +1178,7 @@ static int write_graph_chunk_bloom_indexes(struct hashfile *f,
 	uint32_t cur_pos = 0;
 
 	while (list < last) {
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list);
 		size_t len = filter ? filter->len : 0;
 		cur_pos += len;
 		display_progress(ctx->progress, ++ctx->progress_cnt);
@@ -1215,7 +1218,7 @@ static int write_graph_chunk_bloom_data(struct hashfile *f,
 	hashwrite_be32(f, ctx->bloom_settings->bits_per_entry);
 
 	while (list < last) {
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list);
 		size_t len = filter ? filter->len : 0;
 
 		display_progress(ctx->progress, ++ctx->progress_cnt);
@@ -1385,6 +1388,22 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 	stop_progress(&ctx->progress);
 }
 
+static void trace2_bloom_filter_write_statistics(struct write_commit_graph_context *ctx)
+{
+	struct json_writer jw = JSON_WRITER_INIT;
+
+	jw_object_begin(&jw, 0);
+	jw_object_intmax(&jw, "filter_found_large",
+			 ctx->count_bloom_filter_found_large);
+	jw_object_intmax(&jw, "filter_computed",
+			 ctx->count_bloom_filter_computed);
+	jw_end(&jw);
+
+	trace2_data_json("commit-graph", the_repository, "bloom_statistics", &jw);
+
+	jw_release(&jw);
+}
+
 static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 {
 	int i;
@@ -1407,12 +1426,25 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 		QSORT(sorted_commits, ctx->commits.nr, commit_gen_cmp);
 
 	for (i = 0; i < ctx->commits.nr; i++) {
+		int computed = 0;
 		struct commit *c = sorted_commits[i];
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, c, 1);
+		struct bloom_filter *filter = get_or_compute_bloom_filter(
+			ctx->r,
+			c,
+			1,
+			&computed);
+		if (computed) {
+			ctx->count_bloom_filter_computed++;
+			if (filter && !filter->len)
+				ctx->count_bloom_filter_found_large++;
+		}
 		ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
 		display_progress(progress, i + 1);
 	}
 
+	if (trace2_is_enabled())
+		trace2_bloom_filter_write_statistics(ctx);
+
 	free(sorted_commits);
 	stop_progress(&progress);
 }
diff --git a/line-log.c b/line-log.c
index bf73ea95ac..68eeb425f8 100644
--- a/line-log.c
+++ b/line-log.c
@@ -1159,7 +1159,7 @@ static int bloom_filter_check(struct rev_info *rev,
 		return 1;
 
 	if (!rev->bloom_filter_settings ||
-	    !(filter = get_bloom_filter(rev->repo, commit, 0)))
+	    !(filter = get_bloom_filter(rev->repo, commit)))
 		return 1;
 
 	if (!range)
diff --git a/revision.c b/revision.c
index be600186ee..7f58ecc411 100644
--- a/revision.c
+++ b/revision.c
@@ -751,7 +751,7 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
 	if (commit_graph_generation(commit) == GENERATION_NUMBER_INFINITY)
 		return -1;
 
-	filter = get_bloom_filter(revs->repo, commit, 0);
+	filter = get_bloom_filter(revs->repo, commit);
 
 	if (!filter) {
 		count_bloom_filter_not_present++;
diff --git a/t/helper/test-bloom.c b/t/helper/test-bloom.c
index f0aa80b98e..531af439c2 100644
--- a/t/helper/test-bloom.c
+++ b/t/helper/test-bloom.c
@@ -39,7 +39,8 @@ static void get_bloom_filter_for_commit(const struct object_id *commit_oid)
 	struct bloom_filter *filter;
 	setup_git_directory();
 	c = lookup_commit(the_repository, commit_oid);
-	filter = get_bloom_filter(the_repository, c, 1);
+	filter = get_or_compute_bloom_filter(the_repository, c, 1,
+					     NULL);
 	print_bloom_filter(filter);
 }
 

commit-graph.c, csum-file.h, midx.c

diff --git a/commit-graph.c b/commit-graph.c
index 0d70545149..8964453433 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1784,12 +1784,8 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 
 	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(chunks[i].id);
-		chunk_write[1] = htonl(chunk_offset >> 32);
-		chunk_write[2] = htonl(chunk_offset & 0xffffffff);
-		hashwrite(f, chunk_write, 12);
+		hashwrite_be32(f, chunks[i].id);
+		hashwrite_be64(f, chunk_offset);
 
 		chunk_offset += chunks[i].size;
 	}
diff --git a/csum-file.h b/csum-file.h
index f9cbd317fb..b026ec7766 100644
--- a/csum-file.h
+++ b/csum-file.h
@@ -62,4 +62,10 @@ static inline void hashwrite_be32(struct hashfile *f, uint32_t data)
 	hashwrite(f, &data, sizeof(data));
 }
 
+static inline void hashwrite_be64(struct hashfile *f, uint64_t data)
+{
+	hashwrite_be32(f, data >> 32);
+	hashwrite_be32(f, data & 0xffffffffUL);
+}
+
 #endif
diff --git a/midx.c b/midx.c
index a5fb797ede..51ca27cf34 100644
--- a/midx.c
+++ b/midx.c
@@ -775,8 +775,7 @@ static size_t write_midx_large_offsets(struct hashfile *f, uint32_t nr_large_off
 		if (!(offset >> 31))
 			continue;
 
-		hashwrite_be32(f, offset >> 32);
-		hashwrite_be32(f, offset & 0xffffffffUL);
+		hashwrite_be64(f, offset);
 		written += 2 * sizeof(uint32_t);
 
 		nr_large_offset--;

bloom.c, bloom.h, commit-graph.c, t/helper/test-bloom.c

diff --git a/bloom.c b/bloom.c
index a8a21762f4..0cf1962dc5 100644
--- a/bloom.c
+++ b/bloom.c
@@ -180,13 +180,12 @@ static int pathmap_cmp(const void *hashmap_cmp_fn_data,
 struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 						 struct commit *c,
 						 int compute_if_not_present,
+						 const struct bloom_filter_settings *settings,
 						 int *computed)
 {
 	struct bloom_filter *filter;
-	struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
 	int i;
 	struct diff_options diffopt;
-	int max_changes = 512;
 
 	if (computed)
 		*computed = 0;
@@ -211,7 +210,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 	repo_diff_setup(r, &diffopt);
 	diffopt.flags.recursive = 1;
 	diffopt.detect_rename = 0;
-	diffopt.max_changes = max_changes;
+	diffopt.max_changes = settings->max_changed_paths;
 	diff_setup_done(&diffopt);
 
 	/* ensure commit is parsed so we have parent information */
@@ -223,7 +222,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 		diff_tree_oid(NULL, &c->object.oid, "", &diffopt);
 	diffcore_std(&diffopt);
 
-	if (diffopt.num_changes <= max_changes) {
+	if (diffopt.num_changes <= settings->max_changed_paths) {
 		struct hashmap pathmap;
 		struct pathmap_hash_entry *e;
 		struct hashmap_iter iter;
@@ -260,13 +259,13 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 			diff_free_filepair(diff_queued_diff.queue[i]);
 		}
 
-		filter->len = (hashmap_get_size(&pathmap) * settings.bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
+		filter->len = (hashmap_get_size(&pathmap) * settings->bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
 		filter->data = xcalloc(filter->len, sizeof(unsigned char));
 
 		hashmap_for_each_entry(&pathmap, &iter, e, entry) {
 			struct bloom_key key;
-			fill_bloom_key(e->path, strlen(e->path), &key, &settings);
-			add_key_to_filter(&key, filter, &settings);
+			fill_bloom_key(e->path, strlen(e->path), &key, settings);
+			add_key_to_filter(&key, filter, settings);
 		}
 
 		hashmap_free_entries(&pathmap, struct pathmap_hash_entry, entry);
diff --git a/bloom.h b/bloom.h
index baa91926db..3f19e3fca4 100644
--- a/bloom.h
+++ b/bloom.h
@@ -92,10 +92,11 @@ void init_bloom_filters(void);
 struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 						 struct commit *c,
 						 int compute_if_not_present,
+						 const struct bloom_filter_settings *settings,
 						 int *computed);
 
 #define get_bloom_filter(r, c) get_or_compute_bloom_filter( \
-	(r), (c), 0, NULL)
+	(r), (c), 0, NULL, NULL)
 
 int bloom_filter_contains(const struct bloom_filter *filter,
 			  const struct bloom_key *key,
diff --git a/commit-graph.c b/commit-graph.c
index ba2a2cfb22..48d4697f54 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1432,6 +1432,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 			ctx->r,
 			c,
 			1,
+			ctx->bloom_settings,
 			&computed);
 		if (computed) {
 			ctx->count_bloom_filter_computed++;
@@ -1688,17 +1689,6 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	int num_chunks = 3;
 	uint64_t chunk_offset;
 	struct object_id file_hash;
-	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);
-		bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS",
-							  bloom_settings.max_changed_paths);
-		ctx->bloom_settings = &bloom_settings;
-	}
 
 	if (ctx->split) {
 		struct strbuf tmp_file = STRBUF_INIT;
@@ -2144,6 +2134,7 @@ int write_commit_graph(struct object_directory *odb,
 	uint32_t i, count_distinct = 0;
 	int res = 0;
 	int replace = 0;
+	struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
 
 	if (!commit_graph_compatible(the_repository))
 		return 0;
@@ -2157,6 +2148,14 @@ int write_commit_graph(struct object_directory *odb,
 	ctx->split_opts = split_opts;
 	ctx->total_bloom_filter_data_size = 0;
 
+	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);
+	bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS",
+							 bloom_settings.max_changed_paths);
+	ctx->bloom_settings = &bloom_settings;
+
 	if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS)
 		ctx->changed_paths = 1;
 	if (!(flags & COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS)) {
diff --git a/t/helper/test-bloom.c b/t/helper/test-bloom.c
index 531af439c2..4af949164c 100644
--- a/t/helper/test-bloom.c
+++ b/t/helper/test-bloom.c
@@ -40,6 +40,7 @@ static void get_bloom_filter_for_commit(const struct object_id *commit_oid)
 	setup_git_directory();
 	c = lookup_commit(the_repository, commit_oid);
 	filter = get_or_compute_bloom_filter(the_repository, c, 1,
+					     &settings,
 					     NULL);
 	print_bloom_filter(filter);
 }

bloom.c, diff.h, t/t4216-log-bloom.sh, tree-diff.c

diff --git a/bloom.c b/bloom.c
index 0cf1962dc5..ed54e96e57 100644
--- a/bloom.c
+++ b/bloom.c
@@ -222,7 +222,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 		diff_tree_oid(NULL, &c->object.oid, "", &diffopt);
 	diffcore_std(&diffopt);
 
-	if (diffopt.num_changes <= settings->max_changed_paths) {
+	if (diff_queued_diff.nr <= settings->max_changed_paths) {
 		struct hashmap pathmap;
 		struct pathmap_hash_entry *e;
 		struct hashmap_iter iter;
@@ -259,6 +259,9 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 			diff_free_filepair(diff_queued_diff.queue[i]);
 		}
 
+		if (hashmap_get_size(&pathmap) > settings->max_changed_paths)
+			goto cleanup;
+
 		filter->len = (hashmap_get_size(&pathmap) * settings->bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
 		filter->data = xcalloc(filter->len, sizeof(unsigned char));
 
@@ -268,6 +271,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 			add_key_to_filter(&key, filter, settings);
 		}
 
+	cleanup:
 		hashmap_free_entries(&pathmap, struct pathmap_hash_entry, entry);
 	} else {
 		for (i = 0; i < diff_queued_diff.nr; i++)
diff --git a/diff.h b/diff.h
index e0c0af6286..1d32b71885 100644
--- a/diff.h
+++ b/diff.h
@@ -287,8 +287,6 @@ struct diff_options {
 
 	/* If non-zero, then stop computing after this many changes. */
 	int max_changes;
-	/* For internal use only. */
-	int num_changes;
 
 	int ita_invisible_in_index;
 /* white-space error highlighting */
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index eb2bcc51f0..21b67677ef 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -177,20 +177,87 @@ test_expect_success 'persist filter settings' '
 '
 
 test_expect_success 'correctly report changes over limit' '
-	git init 513changes &&
+	git init limits &&
 	(
-		cd 513changes &&
-		for i in $(test_seq 1 513)
+		cd limits &&
+		mkdir d &&
+		mkdir d/e &&
+
+		for i in $(test_seq 1 2)
 		do
-			echo $i >file$i.txt || return 1
+			printf $i >d/file$i.txt &&
+			printf $i >d/e/file$i.txt || return 1
 		done &&
-		git add . &&
+
+		mkdir mode &&
+		printf bash >mode/script.sh &&
+
+		mkdir foo &&
+		touch foo/bar &&
+		touch foo.txt &&
+
+		git add d foo foo.txt mode &&
 		git commit -m "files" &&
-		git commit-graph write --reachable --changed-paths &&
-		for i in $(test_seq 1 513)
+
+		# Commit has 7 file and 4 directory adds
+		GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=10 \
+			GIT_TRACE2_EVENT="$(pwd)/trace" \
+			git commit-graph write --reachable --changed-paths &&
+		grep "\"max_changed_paths\":10" trace &&
+		grep "\"filter_found_large\":1" trace &&
+
+		for path in $(git ls-tree -r --name-only HEAD)
 		do
-			git -c core.commitGraph=false log -- file$i.txt >expect &&
-			git log -- file$i.txt >actual &&
+			git -c commitGraph.readChangedPaths=false log \
+				-- $path >expect &&
+			git log -- $path >actual &&
+			test_cmp expect actual || return 1
+		done &&
+
+		# Make a variety of path changes
+		printf new1 >d/e/file1.txt &&
+		printf new2 >d/file2.txt &&
+		rm d/e/file2.txt &&
+		rm -r foo &&
+		printf text >foo &&
+		mkdir f &&
+		printf new1 >f/file1.txt &&
+
+		# including a mode-only change (counts as modified)
+		git update-index --chmod=+x mode/script.sh &&
+
+		git add foo d f &&
+		git commit -m "complicated" &&
+
+		# start from scratch and rebuild
+		rm -f .git/objects/info/commit-graph &&
+		GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=10 \
+			GIT_TRACE2_EVENT="$(pwd)/trace-edit" \
+			git commit-graph write --reachable --changed-paths &&
+		grep "\"max_changed_paths\":10" trace-edit &&
+		grep "\"filter_found_large\":2" trace-edit &&
+
+		for path in $(git ls-tree -r --name-only HEAD)
+		do
+			git -c commitGraph.readChangedPaths=false log \
+				-- $path >expect &&
+			git log -- $path >actual &&
+			test_cmp expect actual || return 1
+		done &&
+
+		# start from scratch and rebuild
+		rm -f .git/objects/info/commit-graph &&
+		GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=11 \
+			GIT_TRACE2_EVENT="$(pwd)/trace-update" \
+			git commit-graph write --reachable --changed-paths &&
+		grep "\"max_changed_paths\":11" trace-update &&
+		grep "\"filter_found_large\":0" trace-update &&
+
+		for path in $(git ls-tree -r --name-only HEAD)
+		do
+			git -c commitGraph.readChangedPaths=false log \
+				-- $path >expect &&
+			git log -- $path >actual &&
 			test_cmp expect actual || return 1
 		done
 	)
diff --git a/tree-diff.c b/tree-diff.c
index 6ebad1a46f..7cebbb327e 100644
--- a/tree-diff.c
+++ b/tree-diff.c
@@ -434,7 +434,7 @@ static struct combine_diff_path *ll_diff_tree_paths(
 		if (diff_can_quit_early(opt))
 			break;
 
-		if (opt->max_changes && opt->num_changes > opt->max_changes)
+		if (opt->max_changes && diff_queued_diff.nr > opt->max_changes)
 			break;
 
 		if (opt->pathspec.nr) {
@@ -521,7 +521,6 @@ static struct combine_diff_path *ll_diff_tree_paths(
 
 			/* t↓ */
 			update_tree_entry(&t);
-			opt->num_changes++;
 		}
 
 		/* t > p[imin] */
@@ -539,7 +538,6 @@ static struct combine_diff_path *ll_diff_tree_paths(
 		skip_emit_tp:
 			/* ∀ pi=p[imin]  pi↓ */
 			update_tp_entries(tp, nparent);
-			opt->num_changes++;
 		}
 	}
 
@@ -557,7 +555,6 @@ struct combine_diff_path *diff_tree_paths(
 	const struct object_id **parents_oid, int nparent,
 	struct strbuf *base, struct diff_options *opt)
 {
-	opt->num_changes = 0;
 	p = ll_diff_tree_paths(p, oid, parents_oid, nparent, base, opt);
 
 	/*

diff --git a/commit-graph.c b/commit-graph.c
index 48d4697f54..0d70545149 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -79,10 +79,18 @@ static void set_commit_pos(struct repository *r, const struct object_id *oid)
 	*commit_pos_at(&commit_pos, commit) = max_pos++;
 }
 
-static int commit_pos_cmp(const void *va, const void *vb)
+struct packed_commit_list {
+	struct commit **list;
+	int nr;
+	int alloc;
+};
+
+static int commit_pos_cmp(const void *va, const void *vb, void *ctx)
 {
-	const struct commit *a = *(const struct commit **)va;
-	const struct commit *b = *(const struct commit **)vb;
+	struct packed_commit_list *commits = ctx;
+
+	const struct commit *a = commits->list[*(int *)va];
+	const struct commit *b = commits->list[*(int *)vb];
 	return commit_pos_at(&commit_pos, a) -
 	       commit_pos_at(&commit_pos, b);
 }
@@ -139,10 +147,12 @@ static struct commit_graph_data *commit_graph_data_at(const struct commit *c)
 	return data;
 }
 
-static int commit_gen_cmp(const void *va, const void *vb)
+static int commit_gen_cmp(const void *va, const void *vb, void *ctx)
 {
-	const struct commit *a = *(const struct commit **)va;
-	const struct commit *b = *(const struct commit **)vb;
+	struct packed_commit_list *commits = ctx;
+
+	const struct commit *a = commits->list[*(int *)va];
+	const struct commit *b = commits->list[*(int *)vb];
 
 	uint32_t generation_a = commit_graph_generation(a);
 	uint32_t generation_b = commit_graph_generation(b);
@@ -922,11 +932,6 @@ struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit
 	return get_commit_tree_in_graph_one(r, r->objects->commit_graph, c);
 }
 
-struct packed_commit_list {
-	struct commit **list;
-	int nr;
-	int alloc;
-};
 
 struct packed_oid_list {
 	struct object_id *list;
@@ -1408,7 +1413,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 {
 	int i;
 	struct progress *progress = NULL;
-	struct commit **sorted_commits;
+	int *sorted_commits;
 
 	init_bloom_filters();
 
@@ -1418,16 +1423,16 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 			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++)
+		sorted_commits[i] = i;
+	QSORT_S(sorted_commits, ctx->commits.nr,
+		ctx->order_by_pack ? commit_pos_cmp : commit_gen_cmp,
+		&ctx->commits);
 
 	for (i = 0; i < ctx->commits.nr; i++) {
 		int computed = 0;
-		struct commit *c = sorted_commits[i];
+		int pos = sorted_commits[i];
+		struct commit *c = ctx->commits.list[pos];
 		struct bloom_filter *filter = get_or_compute_bloom_filter(
 			ctx->r,
 			c,

Documentation/technical/commit-graph-format.txt, bloom.h, commit-graph.c, commit-graph.h, t/t4216-log-bloom.sh

diff --git a/Documentation/technical/commit-graph-format.txt b/Documentation/technical/commit-graph-format.txt
index 440541045d..5f2d9ab4d7 100644
--- a/Documentation/technical/commit-graph-format.txt
+++ b/Documentation/technical/commit-graph-format.txt
@@ -123,6 +123,18 @@ CHUNK DATA:
       of length zero.
     * The BDAT chunk is present if and only if BIDX is present.
 
+  Large Bloom Filters (ID: {'B', 'F', 'X', 'L'}) [Optional]
+    * It starts with a 32-bit unsigned integer specifying the maximum number of
+      changed-paths that can be stored in a single Bloom filter.
+    * It then contains a list of 64-bit words (the length of this list is
+      determined by the width of the chunk) which is a bitmap. The 'i'th bit is
+      set exactly when the 'i'th commit in the graph has a changed-path Bloom
+      filter with zero entries (either because the commit is empty, or because
+      it contains more than 512 changed paths).
+    * The BFXL chunk is present only when the BIDX and BDAT chunks are
+      also present.
+
+
   Base Graphs List (ID: {'B', 'A', 'S', 'E'}) [Optional]
       This list of H-byte hashes describe a set of B commit-graph files that
       form a commit-graph chain. The graph position for the ith commit in this
diff --git a/bloom.h b/bloom.h
index 3f19e3fca4..464d9b57de 100644
--- a/bloom.h
+++ b/bloom.h
@@ -33,7 +33,7 @@ struct bloom_filter_settings {
 	 * The maximum number of changed paths per commit
 	 * before declaring a Bloom filter to be too-large.
 	 *
-	 * Not written to the commit-graph file.
+	 * Written to the 'BFXL' chunk (instead of 'BDAT').
 	 */
 	uint32_t max_changed_paths;
 };
diff --git a/commit-graph.c b/commit-graph.c
index 8964453433..ea0583298c 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -41,8 +41,9 @@ void git_test_write_commit_graph_or_die(void)
 #define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
 #define GRAPH_CHUNKID_BLOOMINDEXES 0x42494458 /* "BIDX" */
 #define GRAPH_CHUNKID_BLOOMDATA 0x42444154 /* "BDAT" */
+#define GRAPH_CHUNKID_BLOOMLARGE 0x4246584c /* "BFXL" */
 #define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */
-#define MAX_NUM_CHUNKS 7
+#define MAX_NUM_CHUNKS 8
 
 #define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
 
@@ -429,6 +430,24 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 				graph->bloom_filter_settings->bits_per_entry = get_be32(data + chunk_offset + 8);
 			}
 			break;
+
+		case GRAPH_CHUNKID_BLOOMLARGE:
+			if (graph->chunk_bloom_large_filters)
+				chunk_repeated = 1;
+			else if (r->settings.commit_graph_read_changed_paths) {
+				size_t alloc = get_be64(chunk_lookup + 4) - chunk_offset - sizeof(uint32_t);
+				graph->chunk_bloom_large_filters = data + chunk_offset + sizeof(uint32_t);
+				graph->bloom_filter_settings->max_changed_paths = get_be32(data + chunk_offset);
+				if (alloc) {
+					size_t j;
+					graph->bloom_large = bitmap_word_alloc(alloc);
+
+					for (j = 0; j < graph->bloom_large->word_alloc; j++)
+						graph->bloom_large->words[j] = get_be64(
+							graph->chunk_bloom_large_filters + j * sizeof(eword_t));
+				}
+			}
+			break;
 		}
 
 		if (chunk_repeated) {
@@ -443,7 +462,9 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 		/* We need both the bloom chunks to exist together. Else ignore the data */
 		graph->chunk_bloom_indexes = NULL;
 		graph->chunk_bloom_data = NULL;
+		graph->chunk_bloom_large_filters = NULL;
 		FREE_AND_NULL(graph->bloom_filter_settings);
+		bitmap_free(graph->bloom_large);
 	}
 
 	hashcpy(graph->oid.hash, graph->data + graph->data_len - graph->hash_len);
@@ -932,6 +953,20 @@ struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit
 	return get_commit_tree_in_graph_one(r, r->objects->commit_graph, c);
 }
 
+static int get_bloom_filter_large_in_graph(struct commit_graph *g,
+					   const struct commit *c)
+{
+	uint32_t graph_pos = commit_graph_position(c);
+	if (graph_pos == COMMIT_NOT_FROM_GRAPH)
+		return 0;
+
+	while (g && graph_pos < g->num_commits_in_base)
+		g = g->base_graph;
+
+	if (!(g && g->bloom_large))
+		return 0;
+	return bitmap_get(g->bloom_large, graph_pos - g->num_commits_in_base);
+}
 
 struct packed_oid_list {
 	struct object_id *list;
@@ -970,8 +1005,10 @@ struct write_commit_graph_context {
 	size_t total_bloom_filter_data_size;
 	const struct bloom_filter_settings *bloom_settings;
 
+	int count_bloom_filter_known_large;
 	int count_bloom_filter_found_large;
 	int count_bloom_filter_computed;
+	struct bitmap *bloom_large;
 };
 
 static int write_graph_chunk_fanout(struct hashfile *f,
@@ -1235,6 +1272,23 @@ static int write_graph_chunk_bloom_data(struct hashfile *f,
 	return 0;
 }
 
+static int write_graph_chunk_bloom_large(struct hashfile *f,
+					 struct write_commit_graph_context *ctx)
+{
+	size_t i, alloc = ctx->commits.nr / BITS_IN_EWORD;
+	if (ctx->commits.nr % BITS_IN_EWORD)
+		alloc++;
+	if (alloc > ctx->bloom_large->word_alloc)
+		BUG("write_graph_chunk_bloom_large: bitmap not large enough");
+
+	trace2_region_enter("commit-graph", "bloom_large", ctx->r);
+	hashwrite_be32(f, ctx->bloom_settings->max_changed_paths);
+	for (i = 0; i < ctx->bloom_large->word_alloc; i++)
+		hashwrite_be64(f, ctx->bloom_large->words[i]);
+	trace2_region_leave("commit-graph", "bloom_large", ctx->r);
+	return 0;
+}
+
 static int oid_compare(const void *_a, const void *_b)
 {
 	const struct object_id *a = (const struct object_id *)_a;
@@ -1398,6 +1452,8 @@ static void trace2_bloom_filter_write_statistics(struct write_commit_graph_conte
 	struct json_writer jw = JSON_WRITER_INIT;
 
 	jw_object_begin(&jw, 0);
+	jw_object_intmax(&jw, "filter_known_large",
+			 ctx->count_bloom_filter_known_large);
 	jw_object_intmax(&jw, "filter_found_large",
 			 ctx->count_bloom_filter_found_large);
 	jw_object_intmax(&jw, "filter_computed",
@@ -1416,6 +1472,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 	int *sorted_commits;
 
 	init_bloom_filters();
+	ctx->bloom_large = bitmap_word_alloc(ctx->commits.nr / BITS_IN_EWORD + 1);
 
 	if (ctx->report_progress)
 		progress = start_delayed_progress(
@@ -1430,21 +1487,28 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 		&ctx->commits);
 
 	for (i = 0; i < ctx->commits.nr; i++) {
-		int computed = 0;
 		int pos = sorted_commits[i];
 		struct commit *c = ctx->commits.list[pos];
-		struct bloom_filter *filter = get_or_compute_bloom_filter(
-			ctx->r,
-			c,
-			1,
-			ctx->bloom_settings,
-			&computed);
-		if (computed) {
-			ctx->count_bloom_filter_computed++;
-			if (filter && !filter->len)
-				ctx->count_bloom_filter_found_large++;
+		if (get_bloom_filter_large_in_graph(ctx->r->objects->commit_graph, c)) {
+			bitmap_set(ctx->bloom_large, pos);
+			ctx->count_bloom_filter_known_large++;
+		} else {
+			int computed = 0;
+			struct bloom_filter *filter = get_or_compute_bloom_filter(
+				ctx->r,
+				c,
+				1,
+				ctx->bloom_settings,
+				&computed);
+			if (computed) {
+				ctx->count_bloom_filter_computed++;
+				if (filter && !filter->len) {
+					bitmap_set(ctx->bloom_large, pos);
+					ctx->count_bloom_filter_found_large++;
+				}
+			}
+			ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
 		}
-		ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
 		display_progress(progress, i + 1);
 	}
 
@@ -1764,6 +1828,11 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 					  + ctx->total_bloom_filter_data_size;
 		chunks[num_chunks].write_fn = write_graph_chunk_bloom_data;
 		num_chunks++;
+		chunks[num_chunks].id = GRAPH_CHUNKID_BLOOMLARGE;
+		chunks[num_chunks].size = sizeof(eword_t) * ctx->bloom_large->word_alloc
+					+ sizeof(uint32_t);
+		chunks[num_chunks].write_fn = write_graph_chunk_bloom_large;
+		num_chunks++;
 	}
 	if (ctx->num_commit_graphs_after > 1) {
 		chunks[num_chunks].id = GRAPH_CHUNKID_BASE;
@@ -2503,6 +2572,7 @@ void free_commit_graph(struct commit_graph *g)
 	}
 	free(g->filename);
 	free(g->bloom_filter_settings);
+	bitmap_free(g->bloom_large);
 	free(g);
 }
 
diff --git a/commit-graph.h b/commit-graph.h
index d9acb22bac..ddbca1b59d 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -4,6 +4,7 @@
 #include "git-compat-util.h"
 #include "object-store.h"
 #include "oidset.h"
+#include "ewah/ewok.h"
 
 #define GIT_TEST_COMMIT_GRAPH "GIT_TEST_COMMIT_GRAPH"
 #define GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE "GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE"
@@ -71,6 +72,9 @@ struct commit_graph {
 	const unsigned char *chunk_base_graphs;
 	const unsigned char *chunk_bloom_indexes;
 	const unsigned char *chunk_bloom_data;
+	const unsigned char *chunk_bloom_large_filters;
+
+	struct bitmap *bloom_large;
 
 	struct bloom_filter_settings *bloom_filter_settings;
 };
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index 21b67677ef..6859d85369 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -33,7 +33,7 @@ test_expect_success 'setup test - repo, commits, commit graph, log outputs' '
 	git commit-graph write --reachable --changed-paths
 '
 graph_read_expect () {
-	NUM_CHUNKS=5
+	NUM_CHUNKS=6
 	cat >expect <<- EOF
 	header: 43475048 1 1 $NUM_CHUNKS 0
 	num_commits: $1
@@ -262,5 +262,28 @@ test_expect_success 'correctly report changes over limit' '
 		done
 	)
 '
+test_bloom_filters_computed () {
+	commit_graph_args=$1
+	bloom_trace_prefix="{\"filter_known_large\":$2,\"filter_found_large\":$3,\"filter_computed\":$4"
+	rm -f "$TRASH_DIRECTORY/trace.event" &&
+	GIT_TRACE2_EVENT="$TRASH_DIRECTORY/trace.event" git commit-graph write $commit_graph_args &&
+	grep "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.event"
+}
+
+test_expect_success 'Bloom generation does not recompute too-large filters' '
+	(
+		cd limits &&
+
+		# start from scratch and rebuild
+		rm -f .git/objects/info/commit-graph &&
+		GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=10 \
+			git commit-graph write --reachable --changed-paths \
+			--split=replace &&
+		test_commit c1 filter &&
+
+		test_bloom_filters_computed "--reachable --changed-paths --split=replace" \
+			2 0 1
+	)
+'
 
 test_done

Documentation/technical/commit-graph-format.txt, bloom.h, commit-graph.c, commit-graph.h, t/t4216-log-bloom.sh

diff --git a/Documentation/technical/commit-graph-format.txt b/Documentation/technical/commit-graph-format.txt
index 440541045d..5f2d9ab4d7 100644
--- a/Documentation/technical/commit-graph-format.txt
+++ b/Documentation/technical/commit-graph-format.txt
@@ -123,6 +123,18 @@ CHUNK DATA:
       of length zero.
     * The BDAT chunk is present if and only if BIDX is present.

+  Large Bloom Filters (ID: {'B', 'F', 'X', 'L'}) [Optional]
+    * It starts with a 32-bit unsigned integer specifying the maximum number of
+      changed-paths that can be stored in a single Bloom filter.
+    * It then contains a list of 64-bit words (the length of this list is
+      determined by the width of the chunk) which is a bitmap. The 'i'th bit is
+      set exactly when the 'i'th commit in the graph has a changed-path Bloom
+      filter with zero entries (either because the commit is empty, or because
+      it contains more than 512 changed paths).
+    * The BFXL chunk is present only when the BIDX and BDAT chunks are
+      also present.
+
+
   Base Graphs List (ID: {'B', 'A', 'S', 'E'}) [Optional]
       This list of H-byte hashes describe a set of B commit-graph files that
       form a commit-graph chain. The graph position for the ith commit in this
diff --git a/bloom.h b/bloom.h
index 3f19e3fca4..464d9b57de 100644
--- a/bloom.h
+++ b/bloom.h
@@ -33,7 +33,7 @@ struct bloom_filter_settings {
 	 * The maximum number of changed paths per commit
 	 * before declaring a Bloom filter to be too-large.
 	 *
-	 * Not written to the commit-graph file.
+	 * Written to the 'BFXL' chunk (instead of 'BDAT').
 	 */
 	uint32_t max_changed_paths;
 };
diff --git a/commit-graph.c b/commit-graph.c
index 8964453433..4ccc7a3e56 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -41,8 +41,9 @@ void git_test_write_commit_graph_or_die(void)
 #define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
 #define GRAPH_CHUNKID_BLOOMINDEXES 0x42494458 /* "BIDX" */
 #define GRAPH_CHUNKID_BLOOMDATA 0x42444154 /* "BDAT" */
+#define GRAPH_CHUNKID_BLOOMLARGE 0x4246584c /* "BFXL" */
 #define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */
-#define MAX_NUM_CHUNKS 7
+#define MAX_NUM_CHUNKS 8

 #define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)

@@ -429,6 +430,16 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 				graph->bloom_filter_settings->bits_per_entry = get_be32(data + chunk_offset + 8);
 			}
 			break;
+
+		case GRAPH_CHUNKID_BLOOMLARGE:
+			if (graph->chunk_bloom_large_filters)
+				chunk_repeated = 1;
+			else if (r->settings.commit_graph_read_changed_paths) {
+				graph->chunk_bloom_large_filters = data + chunk_offset + sizeof(uint32_t);
+				graph->bloom_large_alloc = get_be64(chunk_lookup + 4) - chunk_offset - sizeof(uint32_t);
+				graph->bloom_filter_settings->max_changed_paths = get_be32(data + chunk_offset);
+			}
+			break;
 		}

 		if (chunk_repeated) {
@@ -443,6 +454,8 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 		/* We need both the bloom chunks to exist together. Else ignore the data */
 		graph->chunk_bloom_indexes = NULL;
 		graph->chunk_bloom_data = NULL;
+		graph->chunk_bloom_large_filters = NULL;
+		graph->bloom_large_alloc = 0;
 		FREE_AND_NULL(graph->bloom_filter_settings);
 	}

@@ -932,6 +945,32 @@ struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit
 	return get_commit_tree_in_graph_one(r, r->objects->commit_graph, c);
 }

+int get_bloom_filter_large_in_graph(struct commit_graph *g,
+				    const struct commit *c)
+{
+	uint32_t graph_pos = commit_graph_position(c);
+	if (graph_pos == COMMIT_NOT_FROM_GRAPH)
+		return 0;
+
+	while (g && graph_pos < g->num_commits_in_base)
+		g = g->base_graph;
+
+	if (!g)
+		return 0;
+
+	if (!g->bloom_large && g->bloom_large_alloc) {
+		size_t i;
+		g->bloom_large = bitmap_word_alloc(g->bloom_large_alloc);
+
+		for (i = 0; i < g->bloom_large->word_alloc; i++)
+			g->bloom_large->words[i] = get_be64(
+				g->chunk_bloom_large_filters + i * sizeof(eword_t));
+	}
+
+	if (!g->bloom_large)
+		return 0;
+	return bitmap_get(g->bloom_large, graph_pos - g->num_commits_in_base);
+}

 struct packed_oid_list {
 	struct object_id *list;
@@ -970,8 +1009,10 @@ struct write_commit_graph_context {
 	size_t total_bloom_filter_data_size;
 	const struct bloom_filter_settings *bloom_settings;

+	int count_bloom_filter_known_large;
 	int count_bloom_filter_found_large;
 	int count_bloom_filter_computed;
+	struct bitmap *bloom_large;
 };

 static int write_graph_chunk_fanout(struct hashfile *f,
@@ -1235,6 +1276,23 @@ static int write_graph_chunk_bloom_data(struct hashfile *f,
 	return 0;
 }

+static int write_graph_chunk_bloom_large(struct hashfile *f,
+					 struct write_commit_graph_context *ctx)
+{
+	size_t i, alloc = ctx->commits.nr / BITS_IN_EWORD;
+	if (ctx->commits.nr % BITS_IN_EWORD)
+		alloc++;
+	if (alloc > ctx->bloom_large->word_alloc)
+		BUG("write_graph_chunk_bloom_large: bitmap not large enough");
+
+	trace2_region_enter("commit-graph", "bloom_large", ctx->r);
+	hashwrite_be32(f, ctx->bloom_settings->max_changed_paths);
+	for (i = 0; i < ctx->bloom_large->word_alloc; i++)
+		hashwrite_be64(f, ctx->bloom_large->words[i]);
+	trace2_region_leave("commit-graph", "bloom_large", ctx->r);
+	return 0;
+}
+
 static int oid_compare(const void *_a, const void *_b)
 {
 	const struct object_id *a = (const struct object_id *)_a;
@@ -1398,6 +1456,8 @@ static void trace2_bloom_filter_write_statistics(struct write_commit_graph_conte
 	struct json_writer jw = JSON_WRITER_INIT;

 	jw_object_begin(&jw, 0);
+	jw_object_intmax(&jw, "filter_known_large",
+			 ctx->count_bloom_filter_known_large);
 	jw_object_intmax(&jw, "filter_found_large",
 			 ctx->count_bloom_filter_found_large);
 	jw_object_intmax(&jw, "filter_computed",
@@ -1416,6 +1476,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 	int *sorted_commits;

 	init_bloom_filters();
+	ctx->bloom_large = bitmap_word_alloc(ctx->commits.nr / BITS_IN_EWORD + 1);

 	if (ctx->report_progress)
 		progress = start_delayed_progress(
@@ -1430,21 +1491,28 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 		&ctx->commits);

 	for (i = 0; i < ctx->commits.nr; i++) {
-		int computed = 0;
 		int pos = sorted_commits[i];
 		struct commit *c = ctx->commits.list[pos];
-		struct bloom_filter *filter = get_or_compute_bloom_filter(
-			ctx->r,
-			c,
-			1,
-			ctx->bloom_settings,
-			&computed);
-		if (computed) {
-			ctx->count_bloom_filter_computed++;
-			if (filter && !filter->len)
-				ctx->count_bloom_filter_found_large++;
+		if (get_bloom_filter_large_in_graph(ctx->r->objects->commit_graph, c)) {
+			bitmap_set(ctx->bloom_large, pos);
+			ctx->count_bloom_filter_known_large++;
+		} else {
+			int computed = 0;
+			struct bloom_filter *filter = get_or_compute_bloom_filter(
+				ctx->r,
+				c,
+				1,
+				ctx->bloom_settings,
+				&computed);
+			if (computed) {
+				ctx->count_bloom_filter_computed++;
+				if (filter && !filter->len) {
+					bitmap_set(ctx->bloom_large, pos);
+					ctx->count_bloom_filter_found_large++;
+				}
+			}
+			ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
 		}
-		ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
 		display_progress(progress, i + 1);
 	}

@@ -1764,6 +1832,11 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 					  + ctx->total_bloom_filter_data_size;
 		chunks[num_chunks].write_fn = write_graph_chunk_bloom_data;
 		num_chunks++;
+		chunks[num_chunks].id = GRAPH_CHUNKID_BLOOMLARGE;
+		chunks[num_chunks].size = sizeof(eword_t) * ctx->bloom_large->word_alloc
+					+ sizeof(uint32_t);
+		chunks[num_chunks].write_fn = write_graph_chunk_bloom_large;
+		num_chunks++;
 	}
 	if (ctx->num_commit_graphs_after > 1) {
 		chunks[num_chunks].id = GRAPH_CHUNKID_BASE;
@@ -2503,6 +2576,7 @@ void free_commit_graph(struct commit_graph *g)
 	}
 	free(g->filename);
 	free(g->bloom_filter_settings);
+	bitmap_free(g->bloom_large);
 	free(g);
 }

diff --git a/commit-graph.h b/commit-graph.h
index d9acb22bac..9afb1477d5 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -4,6 +4,7 @@
 #include "git-compat-util.h"
 #include "object-store.h"
 #include "oidset.h"
+#include "ewah/ewok.h"

 #define GIT_TEST_COMMIT_GRAPH "GIT_TEST_COMMIT_GRAPH"
 #define GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE "GIT_TEST_COMMIT_GRAPH_DIE_ON_PARSE"
@@ -50,6 +51,9 @@ void load_commit_graph_info(struct repository *r, struct commit *item);
 struct tree *get_commit_tree_in_graph(struct repository *r,
 				      const struct commit *c);

+int get_bloom_filter_large_in_graph(struct commit_graph *g,
+				    const struct commit *c);
+
 struct commit_graph {
 	const unsigned char *data;
 	size_t data_len;
@@ -71,6 +75,10 @@ struct commit_graph {
 	const unsigned char *chunk_base_graphs;
 	const unsigned char *chunk_bloom_indexes;
 	const unsigned char *chunk_bloom_data;
+	const unsigned char *chunk_bloom_large_filters;
+
+	struct bitmap *bloom_large;
+	size_t bloom_large_alloc;

 	struct bloom_filter_settings *bloom_filter_settings;
 };
@@ -83,6 +91,8 @@ struct commit_graph *read_commit_graph_one(struct repository *r,
 struct commit_graph *parse_commit_graph(struct repository *r,
 					void *graph_map, size_t graph_size);

+void prepare_commit_graph_bloom_large(struct commit_graph *g);
+
 /*
  * Return 1 if and only if the repository has a commit-graph
  * file and generation numbers are computed in that file.
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index 21b67677ef..6859d85369 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -33,7 +33,7 @@ test_expect_success 'setup test - repo, commits, commit graph, log outputs' '
 	git commit-graph write --reachable --changed-paths
 '
 graph_read_expect () {
-	NUM_CHUNKS=5
+	NUM_CHUNKS=6
 	cat >expect <<- EOF
 	header: 43475048 1 1 $NUM_CHUNKS 0
 	num_commits: $1
@@ -262,5 +262,28 @@ test_expect_success 'correctly report changes over limit' '
 		done
 	)
 '
+test_bloom_filters_computed () {
+	commit_graph_args=$1
+	bloom_trace_prefix="{\"filter_known_large\":$2,\"filter_found_large\":$3,\"filter_computed\":$4"
+	rm -f "$TRASH_DIRECTORY/trace.event" &&
+	GIT_TRACE2_EVENT="$TRASH_DIRECTORY/trace.event" git commit-graph write $commit_graph_args &&
+	grep "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.event"
+}
+
+test_expect_success 'Bloom generation does not recompute too-large filters' '
+	(
+		cd limits &&
+
+		# start from scratch and rebuild
+		rm -f .git/objects/info/commit-graph &&
+		GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=10 \
+			git commit-graph write --reachable --changed-paths \
+			--split=replace &&
+		test_commit c1 filter &&
+
+		test_bloom_filters_computed "--reachable --changed-paths --split=replace" \
+			2 0 1
+	)
+'

 test_done
--
2.28.0.rc1.13.ge78abce653

builtin/commit-graph.c, commit-graph.c, commit-graph.h

diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index ba5584463f..38f5f57d15 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -119,7 +119,7 @@ static int graph_verify(int argc, const char **argv)
 }
 
 extern int read_replace_refs;
-static struct split_commit_graph_opts split_opts;
+static struct commit_graph_opts write_opts;
 
 static int write_option_parse_split(const struct option *opt, const char *arg,
 				    int unset)
@@ -187,24 +187,24 @@ static int graph_write(int argc, const char **argv)
 		OPT_BOOL(0, "changed-paths", &opts.enable_changed_paths,
 			N_("enable computation for changed paths")),
 		OPT_BOOL(0, "progress", &opts.progress, N_("force progress reporting")),
-		OPT_CALLBACK_F(0, "split", &split_opts.flags, NULL,
+		OPT_CALLBACK_F(0, "split", &write_opts.flags, NULL,
 			N_("allow writing an incremental commit-graph file"),
 			PARSE_OPT_OPTARG | PARSE_OPT_NONEG,
 			write_option_parse_split),
-		OPT_INTEGER(0, "max-commits", &split_opts.max_commits,
+		OPT_INTEGER(0, "max-commits", &write_opts.max_commits,
 			N_("maximum number of commits in a non-base split commit-graph")),
-		OPT_INTEGER(0, "size-multiple", &split_opts.size_multiple,
+		OPT_INTEGER(0, "size-multiple", &write_opts.size_multiple,
 			N_("maximum ratio between two levels of a split commit-graph")),
-		OPT_EXPIRY_DATE(0, "expire-time", &split_opts.expire_time,
+		OPT_EXPIRY_DATE(0, "expire-time", &write_opts.expire_time,
 			N_("only expire files older than a given date-time")),
 		OPT_END(),
 	};
 
 	opts.progress = isatty(2);
 	opts.enable_changed_paths = -1;
-	split_opts.size_multiple = 2;
-	split_opts.max_commits = 0;
-	split_opts.expire_time = 0;
+	write_opts.size_multiple = 2;
+	write_opts.max_commits = 0;
+	write_opts.expire_time = 0;
 
 	trace2_cmd_mode("write");
 
@@ -232,7 +232,7 @@ static int graph_write(int argc, const char **argv)
 	odb = find_odb(the_repository, opts.obj_dir);
 
 	if (opts.reachable) {
-		if (write_commit_graph_reachable(odb, flags, &split_opts))
+		if (write_commit_graph_reachable(odb, flags, &write_opts))
 			return 1;
 		return 0;
 	}
@@ -261,7 +261,7 @@ static int graph_write(int argc, const char **argv)
 			       opts.stdin_packs ? &pack_indexes : NULL,
 			       opts.stdin_commits ? &commits : NULL,
 			       flags,
-			       &split_opts))
+			       &write_opts))
 		result = 1;
 
 cleanup:
diff --git a/commit-graph.c b/commit-graph.c
index ea0583298c..6886f319a5 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1001,7 +1001,7 @@ struct write_commit_graph_context {
 		 changed_paths:1,
 		 order_by_pack:1;
 
-	const struct split_commit_graph_opts *split_opts;
+	const struct commit_graph_opts *opts;
 	size_t total_bloom_filter_data_size;
 	const struct bloom_filter_settings *bloom_settings;
 
@@ -1342,8 +1342,8 @@ 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;
+	enum commit_graph_split_flags flags = ctx->opts ?
+		ctx->opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	if (ctx->report_progress)
 		ctx->progress = start_delayed_progress(
@@ -1543,7 +1543,7 @@ static int add_ref_to_set(const char *refname,
 
 int write_commit_graph_reachable(struct object_directory *odb,
 				 enum commit_graph_write_flags flags,
-				 const struct split_commit_graph_opts *split_opts)
+				 const struct commit_graph_opts *opts)
 {
 	struct oidset commits = OIDSET_INIT;
 	struct refs_cb_data data;
@@ -1560,7 +1560,7 @@ int write_commit_graph_reachable(struct object_directory *odb,
 	stop_progress(&data.progress);
 
 	result = write_commit_graph(odb, NULL, &commits,
-				    flags, split_opts);
+				    flags, opts);
 
 	oidset_clear(&commits);
 	return result;
@@ -1675,8 +1675,8 @@ 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;
+	enum commit_graph_split_flags flags = ctx->opts ?
+		ctx->opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	ctx->num_extra_edges = 0;
 	if (ctx->report_progress)
@@ -1962,13 +1962,13 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 	int max_commits = 0;
 	int size_mult = 2;
 
-	if (ctx->split_opts) {
-		max_commits = ctx->split_opts->max_commits;
+	if (ctx->opts) {
+		max_commits = ctx->opts->max_commits;
 
-		if (ctx->split_opts->size_multiple)
-			size_mult = ctx->split_opts->size_multiple;
+		if (ctx->opts->size_multiple)
+			size_mult = ctx->opts->size_multiple;
 
-		flags = ctx->split_opts->flags;
+		flags = ctx->opts->flags;
 	}
 
 	g = ctx->r->objects->commit_graph;
@@ -2146,8 +2146,8 @@ static void expire_commit_graphs(struct write_commit_graph_context *ctx)
 	size_t dirnamelen;
 	timestamp_t expire_time = time(NULL);
 
-	if (ctx->split_opts && ctx->split_opts->expire_time)
-		expire_time = ctx->split_opts->expire_time;
+	if (ctx->opts && ctx->opts->expire_time)
+		expire_time = ctx->opts->expire_time;
 	if (!ctx->split) {
 		char *chain_file_name = get_chain_filename(ctx->odb);
 		unlink(chain_file_name);
@@ -2198,7 +2198,7 @@ int write_commit_graph(struct object_directory *odb,
 		       struct string_list *pack_indexes,
 		       struct oidset *commits,
 		       enum commit_graph_write_flags flags,
-		       const struct split_commit_graph_opts *split_opts)
+		       const struct commit_graph_opts *opts)
 {
 	struct write_commit_graph_context *ctx;
 	uint32_t i, count_distinct = 0;
@@ -2215,7 +2215,7 @@ 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->split_opts = split_opts;
+	ctx->opts = opts;
 	ctx->total_bloom_filter_data_size = 0;
 
 	bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY",
@@ -2263,15 +2263,15 @@ int write_commit_graph(struct object_directory *odb,
 			}
 		}
 
-		if (ctx->split_opts)
-			replace = ctx->split_opts->flags & COMMIT_GRAPH_SPLIT_REPLACE;
+		if (ctx->opts)
+			replace = ctx->opts->flags & COMMIT_GRAPH_SPLIT_REPLACE;
 	}
 
 	ctx->approx_nr_objects = approximate_object_count();
 	ctx->oids.alloc = ctx->approx_nr_objects / 32;
 
-	if (ctx->split && split_opts && ctx->oids.alloc > split_opts->max_commits)
-		ctx->oids.alloc = split_opts->max_commits;
+	if (ctx->split && opts && ctx->oids.alloc > opts->max_commits)
+		ctx->oids.alloc = opts->max_commits;
 
 	if (ctx->append) {
 		prepare_commit_graph_one(ctx->r, ctx->odb);
diff --git a/commit-graph.h b/commit-graph.h
index ddbca1b59d..af08c4505d 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -109,7 +109,7 @@ enum commit_graph_split_flags {
 	COMMIT_GRAPH_SPLIT_REPLACE          = 2
 };
 
-struct split_commit_graph_opts {
+struct commit_graph_opts {
 	int size_multiple;
 	int max_commits;
 	timestamp_t expire_time;
@@ -124,12 +124,12 @@ struct split_commit_graph_opts {
  */
 int write_commit_graph_reachable(struct object_directory *odb,
 				 enum commit_graph_write_flags flags,
-				 const struct split_commit_graph_opts *split_opts);
+				 const struct commit_graph_opts *opts);
 int write_commit_graph(struct object_directory *odb,
 		       struct string_list *pack_indexes,
 		       struct oidset *commits,
 		       enum commit_graph_write_flags flags,
-		       const struct split_commit_graph_opts *split_opts);
+		       const struct commit_graph_opts *opts);
 
 #define COMMIT_GRAPH_VERIFY_SHALLOW	(1 << 0)
 

Documentation/config/commitgraph.txt, Documentation/git-commit-graph.txt, bloom.c, builtin/commit-graph.c, commit-graph.c, commit-graph.h, t/t4216-log-bloom.sh

diff --git a/Documentation/config/commitgraph.txt b/Documentation/config/commitgraph.txt
index cff0797b54..4582c39fc4 100644
--- a/Documentation/config/commitgraph.txt
+++ b/Documentation/config/commitgraph.txt
@@ -1,3 +1,7 @@
+commitGraph.maxNewFilters::
+	Specifies the default value for the `--max-new-filters` option of `git
+	commit-graph write` (c.f., linkgit:git-commit-graph[1]).
+
 commitGraph.readChangedPaths::
 	If true, then git will use the changed-path Bloom filters in the
 	commit-graph file (if it exists, and they are present). Defaults to
diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt
index 17405c73a9..9c887d5d79 100644
--- a/Documentation/git-commit-graph.txt
+++ b/Documentation/git-commit-graph.txt
@@ -67,6 +67,10 @@ this option is given, future commit-graph writes will automatically assume
 that this option was intended. Use `--no-changed-paths` to stop storing this
 data.
 +
+With the `--max-new-filters=<n>` option, generate at most `n` new Bloom
+filters (if `--changed-paths` is specified). If `n` is `-1`, no limit is
+enforced. Overrides the `commitGraph.maxNewFilters` configuration.
++
 With the `--split[=<strategy>]` option, write the commit-graph as a
 chain of multiple commit-graph files stored in
 `<dir>/info/commit-graphs`. Commit-graph layers are merged based on the
diff --git a/bloom.c b/bloom.c
index ed54e96e57..8d07209c6b 100644
--- a/bloom.c
+++ b/bloom.c
@@ -51,6 +51,21 @@ static int load_bloom_filter_from_graph(struct commit_graph *g,
 	else
 		start_index = 0;
 
+	if ((start_index == end_index) &&
+	    (g->bloom_large && !bitmap_get(g->bloom_large, lex_pos))) {
+		/*
+		 * If the filter is zero-length, either (1) the filter has no
+		 * changes, (2) the filter has too many changes, or (3) it
+		 * wasn't computed (eg., due to '--max-new-filters').
+		 *
+		 * If either (1) or (2) is the case, the 'large' bit will be set
+		 * for this Bloom filter. If it is unset, then it wasn't
+		 * computed. In that case, return nothing, since we don't have
+		 * that filter in the graph.
+		 */
+		return 0;
+	}
+
 	filter->len = end_index - start_index;
 	filter->data = (unsigned char *)(g->chunk_bloom_data +
 					sizeof(unsigned char) * start_index +
diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index 38f5f57d15..3500a6e1f1 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -13,7 +13,8 @@ static char const * const builtin_commit_graph_usage[] = {
 	N_("git commit-graph verify [--object-dir <objdir>] [--shallow] [--[no-]progress]"),
 	N_("git commit-graph write [--object-dir <objdir>] [--append] "
 	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
-	   "[--changed-paths] [--[no-]progress] <split options>"),
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
@@ -25,7 +26,8 @@ static const char * const builtin_commit_graph_verify_usage[] = {
 static const char * const builtin_commit_graph_write_usage[] = {
 	N_("git commit-graph write [--object-dir <objdir>] [--append] "
 	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
-	   "[--changed-paths] [--[no-]progress] <split options>"),
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
@@ -162,6 +164,23 @@ static int read_one_commit(struct oidset *commits, struct progress *progress,
 	return 0;
 }
 
+static int write_option_max_new_filters(const struct option *opt,
+					const char *arg,
+					int unset)
+{
+	int *to = opt->value;
+	if (unset)
+		*to = -1;
+	else {
+		const char *s;
+		*to = strtol(arg, (char **)&s, 10);
+		if (*s)
+			return error(_("%s expects a numerical value"),
+				     optname(opt, opt->flags));
+	}
+	return 0;
+}
+
 static int graph_write(int argc, const char **argv)
 {
 	struct string_list pack_indexes = STRING_LIST_INIT_NODUP;
@@ -197,6 +216,9 @@ static int graph_write(int argc, const char **argv)
 			N_("maximum ratio between two levels of a split commit-graph")),
 		OPT_EXPIRY_DATE(0, "expire-time", &write_opts.expire_time,
 			N_("only expire files older than a given date-time")),
+		OPT_CALLBACK_F(0, "max-new-filters", &write_opts.max_new_filters,
+			NULL, N_("maximum number of changed-path Bloom filters to compute"),
+			0, write_option_max_new_filters),
 		OPT_END(),
 	};
 
@@ -205,6 +227,7 @@ static int graph_write(int argc, const char **argv)
 	write_opts.size_multiple = 2;
 	write_opts.max_commits = 0;
 	write_opts.expire_time = 0;
+	write_opts.max_new_filters = -1;
 
 	trace2_cmd_mode("write");
 
@@ -270,6 +293,16 @@ static int graph_write(int argc, const char **argv)
 	return result;
 }
 
+static int git_commit_graph_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "commitgraph.maxnewfilters")) {
+		write_opts.max_new_filters = git_config_int(var, value);
+		return 0;
+	}
+
+	return git_default_config(var, value, cb);
+}
+
 int cmd_commit_graph(int argc, const char **argv, const char *prefix)
 {
 	static struct option builtin_commit_graph_options[] = {
@@ -283,7 +316,7 @@ int cmd_commit_graph(int argc, const char **argv, const char *prefix)
 		usage_with_options(builtin_commit_graph_usage,
 				   builtin_commit_graph_options);
 
-	git_config(git_default_config, NULL);
+	git_config(git_commit_graph_config, &opts);
 	argc = parse_options(argc, argv, prefix,
 			     builtin_commit_graph_options,
 			     builtin_commit_graph_usage,
diff --git a/commit-graph.c b/commit-graph.c
index 6886f319a5..4aae5471e3 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -954,7 +954,8 @@ struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit
 }
 
 static int get_bloom_filter_large_in_graph(struct commit_graph *g,
-					   const struct commit *c)
+					   const struct commit *c,
+					   uint32_t max_changed_paths)
 {
 	uint32_t graph_pos = commit_graph_position(c);
 	if (graph_pos == COMMIT_NOT_FROM_GRAPH)
@@ -965,6 +966,17 @@ static int get_bloom_filter_large_in_graph(struct commit_graph *g,
 
 	if (!(g && g->bloom_large))
 		return 0;
+	if (g->bloom_filter_settings->max_changed_paths != max_changed_paths) {
+		/*
+		 * Force all commits which are subject to a different
+		 * 'max_changed_paths' limit to be recomputed from scratch.
+		 *
+		 * Note that this could likely be improved, but is ignored since
+		 * all real-world graphs set the maximum number of changed paths
+		 * at 512.
+		 */
+		return 0;
+	}
 	return bitmap_get(g->bloom_large, graph_pos - g->num_commits_in_base);
 }
 
@@ -1470,6 +1482,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 	int i;
 	struct progress *progress = NULL;
 	int *sorted_commits;
+	int max_new_filters;
 
 	init_bloom_filters();
 	ctx->bloom_large = bitmap_word_alloc(ctx->commits.nr / BITS_IN_EWORD + 1);
@@ -1486,10 +1499,15 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 		ctx->order_by_pack ? commit_pos_cmp : commit_gen_cmp,
 		&ctx->commits);
 
+	max_new_filters = ctx->opts->max_new_filters >= 0 ?
+		ctx->opts->max_new_filters : ctx->commits.nr;
+
 	for (i = 0; i < ctx->commits.nr; i++) {
 		int pos = sorted_commits[i];
 		struct commit *c = ctx->commits.list[pos];
-		if (get_bloom_filter_large_in_graph(ctx->r->objects->commit_graph, c)) {
+		if (get_bloom_filter_large_in_graph(ctx->r->objects->commit_graph,
+						    c,
+						    ctx->bloom_settings->max_changed_paths)) {
 			bitmap_set(ctx->bloom_large, pos);
 			ctx->count_bloom_filter_known_large++;
 		} else {
@@ -1497,7 +1515,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 			struct bloom_filter *filter = get_or_compute_bloom_filter(
 				ctx->r,
 				c,
-				1,
+				ctx->count_bloom_filter_computed < max_new_filters,
 				ctx->bloom_settings,
 				&computed);
 			if (computed) {
@@ -1507,7 +1525,8 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 					ctx->count_bloom_filter_found_large++;
 				}
 			}
-			ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
+			if (filter)
+				ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
 		}
 		display_progress(progress, i + 1);
 	}
diff --git a/commit-graph.h b/commit-graph.h
index af08c4505d..75ef83708b 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -114,6 +114,7 @@ struct commit_graph_opts {
 	int max_commits;
 	timestamp_t expire_time;
 	enum commit_graph_split_flags flags;
+	int max_new_filters;
 };
 
 /*
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index 6859d85369..3aab8ffbe3 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -286,4 +286,23 @@ test_expect_success 'Bloom generation does not recompute too-large filters' '
 	)
 '
 
+test_expect_success 'Bloom generation is limited by --max-new-filters' '
+	(
+		cd limits &&
+		test_commit c2 filter &&
+		test_commit c3 filter &&
+		test_commit c4 no-filter &&
+		test_bloom_filters_computed "--reachable --changed-paths --split=replace --max-new-filters=2" \
+			2 0 2
+	)
+'
+
+test_expect_success 'Bloom generation backfills previously-skipped filters' '
+	(
+		cd limits &&
+		test_bloom_filters_computed "--reachable --changed-paths --split=replace --max-new-filters=1" \
+			2 0 1
+	)
+'
+
 test_done

bloom.c, commit-graph.c, commit-graph.h

diff --git a/bloom.c b/bloom.c
index 8d07209c6b..6d0884fa19 100644
--- a/bloom.c
+++ b/bloom.c
@@ -51,21 +51,6 @@ static int load_bloom_filter_from_graph(struct commit_graph *g,
 	else
 		start_index = 0;
 
-	if ((start_index == end_index) &&
-	    (g->bloom_large && !bitmap_get(g->bloom_large, lex_pos))) {
-		/*
-		 * If the filter is zero-length, either (1) the filter has no
-		 * changes, (2) the filter has too many changes, or (3) it
-		 * wasn't computed (eg., due to '--max-new-filters').
-		 *
-		 * If either (1) or (2) is the case, the 'large' bit will be set
-		 * for this Bloom filter. If it is unset, then it wasn't
-		 * computed. In that case, return nothing, since we don't have
-		 * that filter in the graph.
-		 */
-		return 0;
-	}
-
 	filter->len = end_index - start_index;
 	filter->data = (unsigned char *)(g->chunk_bloom_data +
 					sizeof(unsigned char) * start_index +
@@ -212,16 +197,20 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 
 	if (!filter->data) {
 		load_commit_graph_info(r, c);
-		if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH &&
-			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c))
-				return filter;
+		if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH)
+			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c);
 	}
 
-	if (filter->data)
+	if (filter && filter->len)
 		return filter;
 	if (!compute_if_not_present)
 		return NULL;
 
+	if (filter && !filter->len &&
+	    get_bloom_filter_large_in_graph(r->objects->commit_graph, c,
+	    				    settings->max_changed_paths))
+		return filter;
+
 	repo_diff_setup(r, &diffopt);
 	diffopt.flags.recursive = 1;
 	diffopt.detect_rename = 0;
diff --git a/commit-graph.c b/commit-graph.c
index 4aae5471e3..ea89f431cc 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -435,17 +435,9 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 			if (graph->chunk_bloom_large_filters)
 				chunk_repeated = 1;
 			else if (r->settings.commit_graph_read_changed_paths) {
-				size_t alloc = get_be64(chunk_lookup + 4) - chunk_offset - sizeof(uint32_t);
+				graph->bloom_large_alloc = get_be64(chunk_lookup + 4) - chunk_offset - sizeof(uint32_t);
 				graph->chunk_bloom_large_filters = data + chunk_offset + sizeof(uint32_t);
 				graph->bloom_filter_settings->max_changed_paths = get_be32(data + chunk_offset);
-				if (alloc) {
-					size_t j;
-					graph->bloom_large = bitmap_word_alloc(alloc);
-
-					for (j = 0; j < graph->bloom_large->word_alloc; j++)
-						graph->bloom_large->words[j] = get_be64(
-							graph->chunk_bloom_large_filters + j * sizeof(eword_t));
-				}
 			}
 			break;
 		}
@@ -953,9 +945,9 @@ struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit
 	return get_commit_tree_in_graph_one(r, r->objects->commit_graph, c);
 }
 
-static int get_bloom_filter_large_in_graph(struct commit_graph *g,
-					   const struct commit *c,
-					   uint32_t max_changed_paths)
+int get_bloom_filter_large_in_graph(struct commit_graph *g,
+				    const struct commit *c,
+				    uint32_t max_changed_paths)
 {
 	uint32_t graph_pos = commit_graph_position(c);
 	if (graph_pos == COMMIT_NOT_FROM_GRAPH)
@@ -964,8 +956,20 @@ static int get_bloom_filter_large_in_graph(struct commit_graph *g,
 	while (g && graph_pos < g->num_commits_in_base)
 		g = g->base_graph;
 
-	if (!(g && g->bloom_large))
+	if (!g || !g->bloom_large_alloc)
 		return 0;
+
+	if (!g->bloom_large) {
+		size_t j;
+		g->bloom_large = bitmap_word_alloc(g->bloom_large_alloc);
+
+		for (j = 0; j < g->bloom_large->word_alloc; j++) {
+			const void *data = g->chunk_bloom_large_filters +
+					   j * sizeof(eword_t);
+			g->bloom_large->words[j] = get_be64(data);
+		}
+	}
+
 	if (g->bloom_filter_settings->max_changed_paths != max_changed_paths) {
 		/*
 		 * Force all commits which are subject to a different
diff --git a/commit-graph.h b/commit-graph.h
index 75ef83708b..126fd43380 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -51,6 +51,13 @@ void load_commit_graph_info(struct repository *r, struct commit *item);
 struct tree *get_commit_tree_in_graph(struct repository *r,
 				      const struct commit *c);
 
+/*
+ * Returns 1 if this commit was marked in the BFXL chunk as having more
+ * than max_changed_paths changes.
+ */
+int get_bloom_filter_large_in_graph(struct commit_graph *g,
+				    const struct commit *c,
+				    uint32_t max_changed_paths);
 struct commit_graph {
 	const unsigned char *data;
 	size_t data_len;
@@ -74,6 +81,7 @@ struct commit_graph {
 	const unsigned char *chunk_bloom_data;
 	const unsigned char *chunk_bloom_large_filters;
 
+	size_t bloom_large_alloc;
 	struct bitmap *bloom_large;
 
 	struct bloom_filter_settings *bloom_filter_settings;