Merge branch 'ds/omit-trailing-hash-in-index'

Introduce an optional configuration to allow the trailing hash that
protects the index file from bit flipping.

* ds/omit-trailing-hash-in-index:
  features: feature.manyFiles implies fast index writes
  test-lib-functions: add helper for trailing hash
  read-cache: add index.skipHash config option
  hashfile: allow skipping the hash function

Documentation/config/feature.txt

@@ -23,6 +23,11 @@ feature.manyFiles::
 	working directory. With many files, commands such as `git status` and
 	`git checkout` may be slow and these new defaults improve performance:
 +
+* `index.skipHash=true` speeds up index writes by not computing a trailing
+  checksum. Note that this will cause Git versions earlier than 2.13.0 to
+  refuse to parse the index and Git versions earlier than 2.40.0 will report
+  a corrupted index during `git fsck`.
++
 * `index.version=4` enables path-prefix compression in the index.
 +
 * `core.untrackedCache=true` enables the untracked cache. This setting assumes

Documentation/config/index.txt

@@ -30,3 +30,14 @@ index.version::
 	Specify the version with which new index files should be
 	initialized.  This does not affect existing repositories.
 	If `feature.manyFiles` is enabled, then the default is 4.
+
+index.skipHash::
+	When enabled, do not compute the trailing hash for the index file.
+	This accelerates Git commands that manipulate the index, such as
+	`git add`, `git commit`, or `git status`. Instead of storing the
+	checksum, write a trailing set of bytes with value zero, indicating
+	that the computation was skipped.
++
+If you enable `index.skipHash`, then Git clients older than 2.13.0 will
+refuse to parse the index and Git clients older than 2.40.0 will report an
+error during `git fsck`.

csum-file.c

@@ -45,6 +45,7 @@ void hashflush(struct hashfile *f)
 	unsigned offset = f->offset;
 
 	if (offset) {
+		if (!f->skip_hash)
 			the_hash_algo->update_fn(&f->ctx, f->buffer, offset);
 		flush(f, f->buffer, offset);
 		f->offset = 0;
@@ -64,7 +65,12 @@ int finalize_hashfile(struct hashfile *f, unsigned char *result,
 	int fd;
 
 	hashflush(f);
+
+	if (f->skip_hash)
+		hashclr(f->buffer);
+	else
 		the_hash_algo->final_fn(f->buffer, &f->ctx);
+
 	if (result)
 		hashcpy(result, f->buffer);
 	if (flags & CSUM_HASH_IN_STREAM)
@@ -108,6 +114,7 @@ void hashwrite(struct hashfile *f, const void *buf, unsigned int count)
 			 * the hashfile's buffer. In this block,
 			 * f->offset is necessarily zero.
 			 */
+			if (!f->skip_hash)
 				the_hash_algo->update_fn(&f->ctx, buf, nr);
 			flush(f, buf, nr);
 		} else {
@@ -153,6 +160,7 @@ static struct hashfile *hashfd_internal(int fd, const char *name,
 	f->tp = tp;
 	f->name = name;
 	f->do_crc = 0;
+	f->skip_hash = 0;
 	the_hash_algo->init_fn(&f->ctx);
 
 	f->buffer_len = buffer_len;

csum-file.h

@@ -20,6 +20,13 @@ struct hashfile {
 	size_t buffer_len;
 	unsigned char *buffer;
 	unsigned char *check_buffer;
+
+	/**
+	 * If non-zero, skip_hash indicates that we should
+	 * not actually compute the hash for this hashfile and
+	 * instead only use it as a buffered write.
+	 */
+	int skip_hash;
 };
 
 /* Checkpoint */

read-cache.c

@@ -1817,6 +1817,8 @@ static int verify_hdr(const struct cache_header *hdr, unsigned long size)
 	git_hash_ctx c;
 	unsigned char hash[GIT_MAX_RAWSZ];
 	int hdr_version;
+	unsigned char *start, *end;
+	struct object_id oid;
 
 	if (hdr->hdr_signature != htonl(CACHE_SIGNATURE))
 		return error(_("bad signature 0x%08x"), hdr->hdr_signature);
@@ -1827,10 +1829,16 @@ static int verify_hdr(const struct cache_header *hdr, unsigned long size)
 	if (!verify_index_checksum)
 		return 0;
 
+	end = (unsigned char *)hdr + size;
+	start = end - the_hash_algo->rawsz;
+	oidread(&oid, start);
+	if (oideq(&oid, null_oid()))
+		return 0;
+
 	the_hash_algo->init_fn(&c);
 	the_hash_algo->update_fn(&c, hdr, size - the_hash_algo->rawsz);
 	the_hash_algo->final_fn(hash, &c);
-	if (!hasheq(hash, (unsigned char *)hdr + size - the_hash_algo->rawsz))
+	if (!hasheq(hash, start))
 		return error(_("bad index file sha1 signature"));
 	return 0;
 }
@@ -2920,9 +2928,13 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile,
 	int ieot_entries = 1;
 	struct index_entry_offset_table *ieot = NULL;
 	int nr, nr_threads;
+	struct repository *r = istate->repo ? istate->repo : the_repository;
 
 	f = hashfd(tempfile->fd, tempfile->filename.buf);
 
+	prepare_repo_settings(r);
+	f->skip_hash = r->settings.index_skip_hash;
+
 	for (i = removed = extended = 0; i < entries; i++) {
 		if (cache[i]->ce_flags & CE_REMOVE)
 			removed++;

repo-settings.c

@@ -47,6 +47,7 @@ void prepare_repo_settings(struct repository *r)
 	}
 	if (manyfiles) {
 		r->settings.index_version = 4;
+		r->settings.index_skip_hash = 1;
 		r->settings.core_untracked_cache = UNTRACKED_CACHE_WRITE;
 	}
 
@@ -61,6 +62,7 @@ void prepare_repo_settings(struct repository *r)
 	repo_cfg_bool(r, "pack.usesparse", &r->settings.pack_use_sparse, 1);
 	repo_cfg_bool(r, "core.multipackindex", &r->settings.core_multi_pack_index, 1);
 	repo_cfg_bool(r, "index.sparse", &r->settings.sparse_index, 0);
+	repo_cfg_bool(r, "index.skiphash", &r->settings.index_skip_hash, r->settings.index_skip_hash);
 
 	/*
 	 * The GIT_TEST_MULTI_PACK_INDEX variable is special in that

repository.h

@@ -42,6 +42,7 @@ struct repo_settings {
 	struct fsmonitor_settings *fsmonitor; /* lazily loaded */
 
 	int index_version;
+	int index_skip_hash;
 	enum untracked_cache_setting core_untracked_cache;
 
 	int pack_use_sparse;

scalar.c

@@ -143,6 +143,7 @@ static int set_recommended_config(int reconfigure)
 		{ "credential.validate", "false", 1 }, /* GCM4W-only */
 		{ "gc.auto", "0", 1 },
 		{ "gui.GCWarning", "false", 1 },
+		{ "index.skipHash", "false", 1 },
 		{ "index.threads", "true", 1 },
 		{ "index.version", "4", 1 },
 		{ "merge.stat", "false", 1 },

t/t1600-index.sh

@@ -65,6 +65,36 @@ test_expect_success 'out of bounds index.version issues warning' '
 	)
 '
 
+test_expect_success 'index.skipHash config option' '
+	rm -f .git/index &&
+	git -c index.skipHash=true add a &&
+	test_trailing_hash .git/index >hash &&
+	echo $(test_oid zero) >expect &&
+	test_cmp expect hash &&
+	git fsck &&
+
+	rm -f .git/index &&
+	git -c feature.manyFiles=true add a &&
+	test_trailing_hash .git/index >hash &&
+	cmp expect hash &&
+
+	rm -f .git/index &&
+	git -c feature.manyFiles=true \
+	    -c index.skipHash=false add a &&
+	test_trailing_hash .git/index >hash &&
+	! cmp expect hash &&
+
+	test_commit start &&
+	git -c protocol.file.allow=always submodule add ./ sub &&
+	git config index.skipHash false &&
+	git -C sub config index.skipHash true &&
+	>sub/file &&
+	git -C sub add a &&
+	test_trailing_hash .git/modules/sub/index >hash &&
+	test_cmp expect hash &&
+	git -C sub fsck
+'
+
 test_index_version () {
 	INDEX_VERSION_CONFIG=$1 &&
 	FEATURE_MANY_FILES=$2 &&

t/test-lib-functions.sh

@@ -1816,3 +1816,11 @@ test_cmp_config_output () {
 	sort config-actual >sorted-actual &&
 	test_cmp sorted-expect sorted-actual
 }
+
+# Given a filename, extract its trailing hash as a hex string
+test_trailing_hash () {
+	local file="$1" &&
+	tail -c $(test_oid rawsz) "$file" |
+		test-tool hexdump |
+		sed "s/ //g"
+}