Merge branch 'jt/path-filter-fix' into next

The Bloom filter used for path limited history traversal was broken
on systems whose "char" is unsigned; update the implementation and
bump the format version to 2.

* jt/path-filter-fix:
  commit-graph: new filter ver. that fixes murmur3
  repo-settings: introduce commitgraph.changedPathsVersion
  t4216: test changed path filters with high bit paths
  t/helper/test-read-graph: implement `bloom-filters` mode
  bloom.h: make `load_bloom_filter_from_graph()` public
  t/helper/test-read-graph.c: extract `dump_graph_info()`
  gitformat-commit-graph: describe version 2 of BDAT

Author: gitster

Documentation/config/commitgraph.txt

@@ -9,6 +9,26 @@ commitGraph.maxNewFilters::
 	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
-	true. See linkgit:git-commit-graph[1] for more information.
+	Deprecated. Equivalent to commitGraph.changedPathsVersion=-1 if true, and
+	commitGraph.changedPathsVersion=0 if false. (If commitGraph.changedPathVersion
+	is also set, commitGraph.changedPathsVersion takes precedence.)
+
+commitGraph.changedPathsVersion::
+	Specifies the version of the changed-path Bloom filters that Git will read and
+	write. May be -1, 0, 1, or 2.
++
+Defaults to -1.
++
+If -1, Git will use the version of the changed-path Bloom filters in the
+repository, defaulting to 1 if there are none.
++
+If 0, Git will not read any Bloom filters, and will write version 1 Bloom
+filters when instructed to write.
++
+If 1, Git will only read version 1 Bloom filters, and will write version 1
+Bloom filters.
++
+If 2, Git will only read version 2 Bloom filters, and will write version 2
+Bloom filters.
++
+See linkgit:git-commit-graph[1] for more information.

Documentation/gitformat-commit-graph.txt

@@ -142,13 +142,16 @@ All multi-byte numbers are in network byte order.
 
 ==== Bloom Filter Data (ID: {'B', 'D', 'A', 'T'}) [Optional]
     * It starts with header consisting of three unsigned 32-bit integers:
-      - Version of the hash algorithm being used. We currently only support
-	value 1 which corresponds to the 32-bit version of the murmur3 hash
+      - Version of the hash algorithm being used. We currently support
+	value 2 which corresponds to the 32-bit version of the murmur3 hash
 	implemented exactly as described in
 	https://en.wikipedia.org/wiki/MurmurHash#Algorithm and the double
 	hashing technique using seed values 0x293ae76f and 0x7e646e2 as
 	described in https://doi.org/10.1007/978-3-540-30494-4_26 "Bloom Filters
-	in Probabilistic Verification"
+	in Probabilistic Verification". Version 1 Bloom filters have a bug that appears
+	when char is signed and the repository has path names that have characters >=
+	0x80; Git supports reading and writing them, but this ability will be removed
+	in a future version of Git.
       - The number of times a path is hashed and hence the number of bit positions
 	      that cumulatively determine whether a file is present in the commit.
       - The minimum number of bits 'b' per entry in the Bloom filter. If the filter

bloom.c

@@ -29,9 +29,9 @@ static inline unsigned char get_bitmask(uint32_t pos)
 	return ((unsigned char)1) << (pos & (BITS_PER_WORD - 1));
 }
 
-static int load_bloom_filter_from_graph(struct commit_graph *g,
-					struct bloom_filter *filter,
-					uint32_t graph_pos)
+int load_bloom_filter_from_graph(struct commit_graph *g,
+				 struct bloom_filter *filter,
+				 uint32_t graph_pos)
 {
 	uint32_t lex_pos, start_index, end_index;
 
@@ -66,7 +66,64 @@ static int load_bloom_filter_from_graph(struct commit_graph *g,
  * Not considered to be cryptographically secure.
  * Implemented as described in https://en.wikipedia.org/wiki/MurmurHash#Algorithm
  */
-uint32_t murmur3_seeded(uint32_t seed, const char *data, size_t len)
+uint32_t murmur3_seeded_v2(uint32_t seed, const char *data, size_t len)
+{
+	const uint32_t c1 = 0xcc9e2d51;
+	const uint32_t c2 = 0x1b873593;
+	const uint32_t r1 = 15;
+	const uint32_t r2 = 13;
+	const uint32_t m = 5;
+	const uint32_t n = 0xe6546b64;
+	int i;
+	uint32_t k1 = 0;
+	const char *tail;
+
+	int len4 = len / sizeof(uint32_t);
+
+	uint32_t k;
+	for (i = 0; i < len4; i++) {
+		uint32_t byte1 = (uint32_t)(unsigned char)data[4*i];
+		uint32_t byte2 = ((uint32_t)(unsigned char)data[4*i + 1]) << 8;
+		uint32_t byte3 = ((uint32_t)(unsigned char)data[4*i + 2]) << 16;
+		uint32_t byte4 = ((uint32_t)(unsigned char)data[4*i + 3]) << 24;
+		k = byte1 | byte2 | byte3 | byte4;
+		k *= c1;
+		k = rotate_left(k, r1);
+		k *= c2;
+
+		seed ^= k;
+		seed = rotate_left(seed, r2) * m + n;
+	}
+
+	tail = (data + len4 * sizeof(uint32_t));
+
+	switch (len & (sizeof(uint32_t) - 1)) {
+	case 3:
+		k1 ^= ((uint32_t)(unsigned char)tail[2]) << 16;
+		/*-fallthrough*/
+	case 2:
+		k1 ^= ((uint32_t)(unsigned char)tail[1]) << 8;
+		/*-fallthrough*/
+	case 1:
+		k1 ^= ((uint32_t)(unsigned char)tail[0]) << 0;
+		k1 *= c1;
+		k1 = rotate_left(k1, r1);
+		k1 *= c2;
+		seed ^= k1;
+		break;
+	}
+
+	seed ^= (uint32_t)len;
+	seed ^= (seed >> 16);
+	seed *= 0x85ebca6b;
+	seed ^= (seed >> 13);
+	seed *= 0xc2b2ae35;
+	seed ^= (seed >> 16);
+
+	return seed;
+}
+
+static uint32_t murmur3_seeded_v1(uint32_t seed, const char *data, size_t len)
 {
 	const uint32_t c1 = 0xcc9e2d51;
 	const uint32_t c2 = 0x1b873593;
@@ -131,8 +188,14 @@ void fill_bloom_key(const char *data,
 	int i;
 	const uint32_t seed0 = 0x293ae76f;
 	const uint32_t seed1 = 0x7e646e2c;
-	const uint32_t hash0 = murmur3_seeded(seed0, data, len);
-	const uint32_t hash1 = murmur3_seeded(seed1, data, len);
+	uint32_t hash0, hash1;
+	if (settings->hash_version == 2) {
+		hash0 = murmur3_seeded_v2(seed0, data, len);
+		hash1 = murmur3_seeded_v2(seed1, data, len);
+	} else {
+		hash0 = murmur3_seeded_v1(seed0, data, len);
+		hash1 = murmur3_seeded_v1(seed1, data, len);
+	}
 
 	key->hashes = (uint32_t *)xcalloc(settings->num_hashes, sizeof(uint32_t));
 	for (i = 0; i < settings->num_hashes; i++)

bloom.h

@@ -3,13 +3,16 @@
 
 struct commit;
 struct repository;
+struct commit_graph;
 
 struct bloom_filter_settings {
 	/*
 	 * The version of the hashing technique being used.
-	 * We currently only support version = 1 which is
+	 * The newest version is 2, which is
 	 * the seeded murmur3 hashing technique implemented
-	 * in bloom.c.
+	 * in bloom.c. Bloom filters of version 1 were created
+	 * with prior versions of Git, which had a bug in the
+	 * implementation of the hash function.
 	 */
 	uint32_t hash_version;
 
@@ -68,14 +71,18 @@ struct bloom_key {
 	uint32_t *hashes;
 };
 
+int load_bloom_filter_from_graph(struct commit_graph *g,
+				 struct bloom_filter *filter,
+				 uint32_t graph_pos);
+
 /*
  * Calculate the murmur3 32-bit hash value for the given data
  * using the given seed.
  * Produces a uniformly distributed hash value.
  * Not considered to be cryptographically secure.
  * Implemented as described in https://en.wikipedia.org/wiki/MurmurHash#Algorithm
  */
-uint32_t murmur3_seeded(uint32_t seed, const char *data, size_t len);
+uint32_t murmur3_seeded_v2(uint32_t seed, const char *data, size_t len);
 
 void fill_bloom_key(const char *data,
 		    size_t len,

commit-graph.c

@@ -304,17 +304,26 @@ static int graph_read_oid_lookup(const unsigned char *chunk_start,
 	return 0;
 }
 
+struct graph_read_bloom_data_context {
+	struct commit_graph *g;
+	int *commit_graph_changed_paths_version;
+};
+
 static int graph_read_bloom_data(const unsigned char *chunk_start,
 				  size_t chunk_size, void *data)
 {
-	struct commit_graph *g = data;
+	struct graph_read_bloom_data_context *c = data;
+	struct commit_graph *g = c->g;
 	uint32_t hash_version;
-	g->chunk_bloom_data = chunk_start;
 	hash_version = get_be32(chunk_start);
 
-	if (hash_version != 1)
+	if (*c->commit_graph_changed_paths_version == -1) {
+		*c->commit_graph_changed_paths_version = hash_version;
+	} else if (hash_version != *c->commit_graph_changed_paths_version) {
 		return 0;
+	}
 
+	g->chunk_bloom_data = chunk_start;
 	g->bloom_filter_settings = xmalloc(sizeof(struct bloom_filter_settings));
 	g->bloom_filter_settings->hash_version = hash_version;
 	g->bloom_filter_settings->num_hashes = get_be32(chunk_start + 4);
@@ -401,11 +410,15 @@ struct commit_graph *parse_commit_graph(struct repo_settings *s,
 			graph->read_generation_data = 1;
 	}
 
-	if (s->commit_graph_read_changed_paths) {
+	if (s->commit_graph_changed_paths_version) {
+		struct graph_read_bloom_data_context context = {
+			.g = graph,
+			.commit_graph_changed_paths_version = &s->commit_graph_changed_paths_version
+		};
 		pair_chunk(cf, GRAPH_CHUNKID_BLOOMINDEXES,
 			   &graph->chunk_bloom_indexes);
 		read_chunk(cf, GRAPH_CHUNKID_BLOOMDATA,
-			   graph_read_bloom_data, graph);
+			   graph_read_bloom_data, &context);
 	}
 
 	if (graph->chunk_bloom_indexes && graph->chunk_bloom_data) {
@@ -2388,6 +2401,14 @@ int write_commit_graph(struct object_directory *odb,
 	ctx->write_generation_data = (get_configured_generation_version(r) == 2);
 	ctx->num_generation_data_overflows = 0;
 
+	if (r->settings.commit_graph_changed_paths_version < -1
+	    || r->settings.commit_graph_changed_paths_version > 2) {
+		warning(_("attempting to write a commit-graph, but 'commitgraph.changedPathsVersion' (%d) is not supported"),
+			r->settings.commit_graph_changed_paths_version);
+		return 0;
+	}
+	bloom_settings.hash_version = r->settings.commit_graph_changed_paths_version == 2
+		? 2 : 1;
 	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",
@@ -2417,7 +2438,7 @@ int write_commit_graph(struct object_directory *odb,
 		g = ctx->r->objects->commit_graph;
 
 		/* We have changed-paths already. Keep them in the next graph */
-		if (g && g->chunk_bloom_data) {
+		if (g && g->bloom_filter_settings) {
 			ctx->changed_paths = 1;
 			ctx->bloom_settings = g->bloom_filter_settings;
 		}

oss-fuzz/fuzz-commit-graph.c

@@ -19,7 +19,7 @@ int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size)
 	 * possible.
 	 */
 	the_repository->settings.commit_graph_generation_version = 2;
-	the_repository->settings.commit_graph_read_changed_paths = 1;
+	the_repository->settings.commit_graph_changed_paths_version = 1;
 	g = parse_commit_graph(&the_repository->settings, (void *)data, size);
 	repo_clear(the_repository);
 	free_commit_graph(g);

repo-settings.c

@@ -24,6 +24,7 @@ void prepare_repo_settings(struct repository *r)
 	int value;
 	const char *strval;
 	int manyfiles;
+	int read_changed_paths;
 
 	if (!r->gitdir)
 		BUG("Cannot add settings for uninitialized repository");
@@ -54,7 +55,10 @@ void prepare_repo_settings(struct repository *r)
 	/* Commit graph config or default, does not cascade (simple) */
 	repo_cfg_bool(r, "core.commitgraph", &r->settings.core_commit_graph, 1);
 	repo_cfg_int(r, "commitgraph.generationversion", &r->settings.commit_graph_generation_version, 2);
-	repo_cfg_bool(r, "commitgraph.readchangedpaths", &r->settings.commit_graph_read_changed_paths, 1);
+	repo_cfg_bool(r, "commitgraph.readchangedpaths", &read_changed_paths, 1);
+	repo_cfg_int(r, "commitgraph.changedpathsversion",
+		     &r->settings.commit_graph_changed_paths_version,
+		     read_changed_paths ? -1 : 0);
 	repo_cfg_bool(r, "gc.writecommitgraph", &r->settings.gc_write_commit_graph, 1);
 	repo_cfg_bool(r, "fetch.writecommitgraph", &r->settings.fetch_write_commit_graph, 0);
 

repository.h

@@ -29,7 +29,7 @@ struct repo_settings {
 
 	int core_commit_graph;
 	int commit_graph_generation_version;
-	int commit_graph_read_changed_paths;
+	int commit_graph_changed_paths_version;
 	int gc_write_commit_graph;
 	int fetch_write_commit_graph;
 	int command_requires_full_index;

t/helper/test-bloom.c

@@ -50,6 +50,7 @@ static void get_bloom_filter_for_commit(const struct object_id *commit_oid)
 
 static const char *bloom_usage = "\n"
 "  test-tool bloom get_murmur3 <string>\n"
+"  test-tool bloom get_murmur3_seven_highbit\n"
 "  test-tool bloom generate_filter <string> [<string>...]\n"
 "  test-tool bloom get_filter_for_commit <commit-hex>\n";
 
@@ -64,7 +65,13 @@ int cmd__bloom(int argc, const char **argv)
 		uint32_t hashed;
 		if (argc < 3)
 			usage(bloom_usage);
-		hashed = murmur3_seeded(0, argv[2], strlen(argv[2]));
+		hashed = murmur3_seeded_v2(0, argv[2], strlen(argv[2]));
+		printf("Murmur3 Hash with seed=0:0x%08x\n", hashed);
+	}
+
+	if (!strcmp(argv[1], "get_murmur3_seven_highbit")) {
+		uint32_t hashed;
+		hashed = murmur3_seeded_v2(0, "\x99\xaa\xbb\xcc\xdd\xee\xff", 7);
 		printf("Murmur3 Hash with seed=0:0x%08x\n", hashed);
 	}