Merge branch 'ds/sha256-leftover-bits'

midx and commit-graph files now use the byte defined in their file
format specification for identifying the hash function used for
object names.

* ds/sha256-leftover-bits:
  multi-pack-index: use hash version byte
  commit-graph: use the "hash version" byte
  t/README: document GIT_TEST_DEFAULT_HASH

Documentation/technical/commit-graph-format.txt

@@ -42,8 +42,13 @@ HEADER:
   1-byte version number:
       Currently, the only valid version is 1.
 
-  1-byte Hash Version (1 = SHA-1)
+  1-byte Hash Version
-      We infer the hash length (H) from this value.
+      We infer the hash length (H) from this value:
+	1 => SHA-1
+	2 => SHA-256
+      If the hash type does not match the repository's hash algorithm, the
+      commit-graph file should be ignored with a warning presented to the
+      user.
 
   1-byte number (C) of "chunks"
 

Documentation/technical/pack-format.txt

@@ -279,7 +279,12 @@ HEADER:
 	    Git only writes or recognizes version 1.
 
 	1-byte Object Id Version
-	    Git only writes or recognizes version 1 (SHA1).
+	    We infer the length of object IDs (OIDs) from this value:
+		1 => SHA-1
+		2 => SHA-256
+	    If the hash type does not match the repository's hash algorithm,
+	    the multi-pack-index file should be ignored with a warning
+	    presented to the user.
 
 	1-byte number of "chunks"
 

commit-graph.c

@@ -179,7 +179,14 @@ static char *get_chain_filename(struct object_directory *odb)
 
 static uint8_t oid_version(void)
 {
-	return 1;
+	switch (hash_algo_by_ptr(the_hash_algo)) {
+	case GIT_HASH_SHA1:
+		return 1;
+	case GIT_HASH_SHA256:
+		return 2;
+	default:
+		die(_("invalid hash version"));
+	}
 }
 
 static struct commit_graph *alloc_commit_graph(void)

midx.c

@@ -17,7 +17,6 @@
 #define MIDX_BYTE_HASH_VERSION 5
 #define MIDX_BYTE_NUM_CHUNKS 6
 #define MIDX_BYTE_NUM_PACKS 8
-#define MIDX_HASH_VERSION 1
 #define MIDX_HEADER_SIZE 12
 #define MIDX_MIN_SIZE (MIDX_HEADER_SIZE + the_hash_algo->rawsz)
 
@@ -36,6 +35,18 @@
 
 #define PACK_EXPIRED UINT_MAX
 
+static uint8_t oid_version(void)
+{
+	switch (hash_algo_by_ptr(the_hash_algo)) {
+	case GIT_HASH_SHA1:
+		return 1;
+	case GIT_HASH_SHA256:
+		return 2;
+	default:
+		die(_("invalid hash version"));
+	}
+}
+
 static char *get_midx_filename(const char *object_dir)
 {
 	return xstrfmt("%s/pack/multi-pack-index", object_dir);
@@ -90,8 +101,11 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local
 		      m->version);
 
 	hash_version = m->data[MIDX_BYTE_HASH_VERSION];
-	if (hash_version != MIDX_HASH_VERSION)
+	if (hash_version != oid_version()) {
-		die(_("hash version %u does not match"), hash_version);
+		error(_("multi-pack-index hash version %u does not match version %u"),
+		      hash_version, oid_version());
+		goto cleanup_fail;
+	}
 	m->hash_len = the_hash_algo->rawsz;
 
 	m->num_chunks = m->data[MIDX_BYTE_NUM_CHUNKS];
@@ -418,7 +432,7 @@ static size_t write_midx_header(struct hashfile *f,
 
 	hashwrite_be32(f, MIDX_SIGNATURE);
 	byte_values[0] = MIDX_VERSION;
-	byte_values[1] = MIDX_HASH_VERSION;
+	byte_values[1] = oid_version();
 	byte_values[2] = num_chunks;
 	byte_values[3] = 0; /* unused */
 	hashwrite(f, byte_values, sizeof(byte_values));
@@ -1105,8 +1119,17 @@ int verify_midx_file(struct repository *r, const char *object_dir, unsigned flag
 	struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
 	verify_midx_error = 0;
 
-	if (!m)
+	if (!m) {
-		return 0;
+		int result = 0;
+		struct stat sb;
+		char *filename = get_midx_filename(object_dir);
+		if (!stat(filename, &sb)) {
+			error(_("multi-pack-index file exists, but failed to parse"));
+			result = 1;
+		}
+		free(filename);
+		return result;
+	}
 
 	if (flags & MIDX_PROGRESS)
 		progress = start_progress(_("Looking for referenced packfiles"),

t/README

@@ -421,6 +421,10 @@ GIT_TEST_DISALLOW_ABBREVIATED_OPTIONS=<boolean>, when true (which is
 the default when running tests), errors out when an abbreviated option
 is used.
 
+GIT_TEST_DEFAULT_HASH=<hash-algo> specifies which hash algorithm to
+use in the test scripts. Recognized values for <hash-algo> are "sha1"
+and "sha256".
+
 Naming Tests
 ------------
 

t/helper/test-read-midx.c

@@ -7,14 +7,18 @@
 static int read_midx_file(const char *object_dir)
 {
 	uint32_t i;
-	struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
+	struct multi_pack_index *m;
+
+	setup_git_directory();
+	m = load_multi_pack_index(object_dir, 1);
 
 	if (!m)
 		return 1;
 
-	printf("header: %08x %d %d %d\n",
+	printf("header: %08x %d %d %d %d\n",
 	       m->signature,
 	       m->version,
+	       m->hash_len,
 	       m->num_chunks,
 	       m->num_packs);
 

t/t4216-log-bloom.sh

@@ -30,12 +30,17 @@ test_expect_success 'setup test - repo, commits, commit graph, log outputs' '
 	rm file_to_be_deleted &&
 	git add . &&
 	git commit -m "file removed" &&
-	git commit-graph write --reachable --changed-paths
+	git commit-graph write --reachable --changed-paths &&
+
+	test_oid_cache <<-EOF
+	oid_version sha1:1
+	oid_version sha256:2
+	EOF
 '
 graph_read_expect () {
 	NUM_CHUNKS=5
 	cat >expect <<- EOF
-	header: 43475048 1 1 $NUM_CHUNKS 0
+	header: 43475048 1 $(test_oid oid_version) $NUM_CHUNKS 0
 	num_commits: $1
 	chunks: oid_fanout oid_lookup commit_metadata bloom_indexes bloom_data
 	EOF

t/t5318-commit-graph.sh

@@ -10,7 +10,12 @@ test_expect_success 'setup full repo' '
 	cd "$TRASH_DIRECTORY/full" &&
 	git init &&
 	git config core.commitGraph true &&
-	objdir=".git/objects"
+	objdir=".git/objects" &&
+
+	test_oid_cache <<-EOF
+	oid_version sha1:1
+	oid_version sha256:2
+	EOF
 '
 
 test_expect_success POSIXPERM 'tweak umask for modebit tests' '
@@ -77,7 +82,7 @@ graph_read_expect() {
 		NUM_CHUNKS=$((3 + $(echo "$2" | wc -w)))
 	fi
 	cat >expect <<- EOF
-	header: 43475048 1 1 $NUM_CHUNKS 0
+	header: 43475048 1 $(test_oid oid_version) $NUM_CHUNKS 0
 	num_commits: $1
 	chunks: oid_fanout oid_lookup commit_metadata$OPTIONAL
 	EOF
@@ -412,6 +417,35 @@ test_expect_success 'replace-objects invalidates commit-graph' '
 	)
 '
 
+test_expect_success 'warn on improper hash version' '
+	git init --object-format=sha1 sha1 &&
+	(
+		cd sha1 &&
+		test_commit 1 &&
+		git commit-graph write --reachable &&
+		mv .git/objects/info/commit-graph ../cg-sha1
+	) &&
+	git init --object-format=sha256 sha256 &&
+	(
+		cd sha256 &&
+		test_commit 1 &&
+		git commit-graph write --reachable &&
+		mv .git/objects/info/commit-graph ../cg-sha256
+	) &&
+	(
+		cd sha1 &&
+		mv ../cg-sha256 .git/objects/info/commit-graph &&
+		git log -1 2>err &&
+		test_i18ngrep "commit-graph hash version 2 does not match version 1" err
+	) &&
+	(
+		cd sha256 &&
+		mv ../cg-sha1 .git/objects/info/commit-graph &&
+		git log -1 2>err &&
+		test_i18ngrep "commit-graph hash version 1 does not match version 2" err
+	)
+'
+
 # the verify tests below expect the commit-graph to contain
 # exactly the commits reachable from the commits/8 branch.
 # If the file changes the set of commits in the list, then the

t/t5319-multi-pack-index.sh

@@ -5,6 +5,8 @@ test_description='multi-pack-indexes'
 
 objdir=.git/objects
 
+HASH_LEN=$(test_oid rawsz)
+
 midx_read_expect () {
 	NUM_PACKS=$1
 	NUM_OBJECTS=$2
@@ -13,7 +15,7 @@ midx_read_expect () {
 	EXTRA_CHUNKS="$5"
 	{
 		cat <<-EOF &&
-		header: 4d494458 1 $NUM_CHUNKS $NUM_PACKS
+		header: 4d494458 1 $HASH_LEN $NUM_CHUNKS $NUM_PACKS
 		chunks: pack-names oid-fanout oid-lookup object-offsets$EXTRA_CHUNKS
 		num_objects: $NUM_OBJECTS
 		packs:
@@ -46,7 +48,7 @@ test_expect_success "don't write midx with no packs" '
 	test_path_is_missing pack/multi-pack-index
 '
 
-test_expect_success "Warn if a midx contains no oid" '
+test_expect_success SHA1 'warn if a midx contains no oid' '
 	cp "$TEST_DIRECTORY"/t5319/no-objects.midx $objdir/pack/multi-pack-index &&
 	test_must_fail git multi-pack-index verify &&
 	rm $objdir/pack/multi-pack-index
@@ -198,6 +200,40 @@ test_expect_success 'write midx with twelve packs' '
 
 compare_results_with_midx "twelve packs"
 
+test_expect_success 'warn on improper hash version' '
+	git init --object-format=sha1 sha1 &&
+	(
+		cd sha1 &&
+		git config core.multiPackIndex true &&
+		test_commit 1 &&
+		git repack -a &&
+		git multi-pack-index write &&
+		mv .git/objects/pack/multi-pack-index ../mpi-sha1
+	) &&
+	git init --object-format=sha256 sha256 &&
+	(
+		cd sha256 &&
+		git config core.multiPackIndex true &&
+		test_commit 1 &&
+		git repack -a &&
+		git multi-pack-index write &&
+		mv .git/objects/pack/multi-pack-index ../mpi-sha256
+	) &&
+	(
+		cd sha1 &&
+		mv ../mpi-sha256 .git/objects/pack/multi-pack-index &&
+		git log -1 2>err &&
+		test_i18ngrep "multi-pack-index hash version 2 does not match version 1" err
+	) &&
+	(
+		cd sha256 &&
+		mv ../mpi-sha1 .git/objects/pack/multi-pack-index &&
+		git log -1 2>err &&
+		test_i18ngrep "multi-pack-index hash version 1 does not match version 2" err
+	)
+'
+
+
 test_expect_success 'verify multi-pack-index success' '
 	git multi-pack-index verify --object-dir=$objdir
 '
@@ -243,7 +279,6 @@ test_expect_success 'verify bad signature' '
 		"multi-pack-index signature"
 '
 
-HASH_LEN=$(test_oid rawsz)
 NUM_OBJECTS=74
 MIDX_BYTE_VERSION=4
 MIDX_BYTE_OID_VERSION=5
@@ -272,7 +307,7 @@ test_expect_success 'verify bad version' '
 '
 
 test_expect_success 'verify bad OID version' '
-	corrupt_midx_and_verify $MIDX_BYTE_OID_VERSION "\02" $objdir \
+	corrupt_midx_and_verify $MIDX_BYTE_OID_VERSION "\03" $objdir \
 		"hash version"
 '
 

t/t5324-split-commit-graph.sh

@@ -18,6 +18,9 @@ test_expect_success 'setup repo' '
 
 	base sha1:1376
 	base sha256:1496
+
+	oid_version sha1:1
+	oid_version sha256:2
 	EOM
 '
 
@@ -28,7 +31,7 @@ graph_read_expect() {
 		NUM_BASE=$2
 	fi
 	cat >expect <<- EOF
-	header: 43475048 1 1 3 $NUM_BASE
+	header: 43475048 1 $(test_oid oid_version) 3 $NUM_BASE
 	num_commits: $1
 	chunks: oid_fanout oid_lookup commit_metadata
 	EOF