Merge branch 'jc/index-pack'

* jc/index-pack:
  verify-pack: use index-pack --verify
  index-pack: show histogram when emulating "verify-pack -v"
  index-pack: start learning to emulate "verify-pack -v"
  index-pack: a miniscule refactor
  index-pack --verify: read anomalous offsets from v2 idx file
  write_idx_file: need_large_offset() helper function
  index-pack: --verify
  write_idx_file: introduce a struct to hold idx customization options
  index-pack: group the delta-base array entries also by type

Conflicts:
	builtin/verify-pack.c
	cache.h
	sha1_file.c

builtin/index-pack.c

@@ -11,7 +11,7 @@
 #include "exec_cmd.h"
 
 static const char index_pack_usage[] =
-"git index-pack [-v] [-o <index-file>] [ --keep | --keep=<msg> ] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
+"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
 
 struct object_entry {
 	struct pack_idx_entry idx;
@@ -19,6 +19,8 @@ struct object_entry {
 	unsigned int hdr_size;
 	enum object_type type;
 	enum object_type real_type;
+	unsigned delta_depth;
+	int base_object_no;
 };
 
 union delta_base {
@@ -66,6 +68,7 @@ static struct progress *progress;
 static unsigned char input_buffer[4096];
 static unsigned int input_offset, input_len;
 static off_t consumed_bytes;
+static unsigned deepest_delta;
 static git_SHA_CTX input_ctx;
 static uint32_t input_crc32;
 static int input_fd, output_fd, pack_fd;
@@ -389,7 +392,18 @@ static void *get_data_from_pack(struct object_entry *obj)
 	return data;
 }
 
-static int find_delta(const union delta_base *base)
+static int compare_delta_bases(const union delta_base *base1,
+			       const union delta_base *base2,
+			       enum object_type type1,
+			       enum object_type type2)
+{
+	int cmp = type1 - type2;
+	if (cmp)
+		return cmp;
+	return memcmp(base1, base2, UNION_BASE_SZ);
+}
+
+static int find_delta(const union delta_base *base, enum object_type type)
 {
 	int first = 0, last = nr_deltas;
 
@@ -398,7 +412,8 @@ static int find_delta(const union delta_base *base)
                 struct delta_entry *delta = &deltas[next];
                 int cmp;
 
-                cmp = memcmp(base, &delta->base, UNION_BASE_SZ);
+		cmp = compare_delta_bases(base, &delta->base,
+					  type, objects[delta->obj_no].type);
                 if (!cmp)
                         return next;
                 if (cmp < 0) {
@@ -411,9 +426,10 @@ static int find_delta(const union delta_base *base)
 }
 
 static void find_delta_children(const union delta_base *base,
-				int *first_index, int *last_index)
+				int *first_index, int *last_index,
+				enum object_type type)
 {
-	int first = find_delta(base);
+	int first = find_delta(base, type);
 	int last = first;
 	int end = nr_deltas - 1;
 
@@ -483,12 +499,17 @@ static void sha1_object(const void *data, unsigned long size,
 	}
 }
 
+static int is_delta_type(enum object_type type)
+{
+	return (type == OBJ_REF_DELTA || type == OBJ_OFS_DELTA);
+}
+
 static void *get_base_data(struct base_data *c)
 {
 	if (!c->data) {
 		struct object_entry *obj = c->obj;
 
-		if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
+		if (is_delta_type(obj->type)) {
 			void *base = get_base_data(c->base);
 			void *raw = get_data_from_pack(obj);
 			c->data = patch_delta(
@@ -515,6 +536,10 @@ static void resolve_delta(struct object_entry *delta_obj,
 	void *base_data, *delta_data;
 
 	delta_obj->real_type = base->obj->real_type;
+	delta_obj->delta_depth = base->obj->delta_depth + 1;
+	if (deepest_delta < delta_obj->delta_depth)
+		deepest_delta = delta_obj->delta_depth;
+	delta_obj->base_object_no = base->obj - objects;
 	delta_data = get_data_from_pack(delta_obj);
 	base_data = get_base_data(base);
 	result->obj = delta_obj;
@@ -541,11 +566,13 @@ static void find_unresolved_deltas(struct base_data *base,
 		union delta_base base_spec;
 
 		hashcpy(base_spec.sha1, base->obj->idx.sha1);
-		find_delta_children(&base_spec, &ref_first, &ref_last);
+		find_delta_children(&base_spec,
+				    &ref_first, &ref_last, OBJ_REF_DELTA);
 
 		memset(&base_spec, 0, sizeof(base_spec));
 		base_spec.offset = base->obj->idx.offset;
-		find_delta_children(&base_spec, &ofs_first, &ofs_last);
+		find_delta_children(&base_spec,
+				    &ofs_first, &ofs_last, OBJ_OFS_DELTA);
 	}
 
 	if (ref_last == -1 && ofs_last == -1) {
@@ -557,24 +584,24 @@ static void find_unresolved_deltas(struct base_data *base,
 
 	for (i = ref_first; i <= ref_last; i++) {
 		struct object_entry *child = objects + deltas[i].obj_no;
-		if (child->real_type == OBJ_REF_DELTA) {
+		struct base_data result;
-			struct base_data result;
+
-			resolve_delta(child, base, &result);
+		assert(child->real_type == OBJ_REF_DELTA);
-			if (i == ref_last && ofs_last == -1)
+		resolve_delta(child, base, &result);
-				free_base_data(base);
+		if (i == ref_last && ofs_last == -1)
-			find_unresolved_deltas(&result, base);
+			free_base_data(base);
-		}
+		find_unresolved_deltas(&result, base);
 	}
 
 	for (i = ofs_first; i <= ofs_last; i++) {
 		struct object_entry *child = objects + deltas[i].obj_no;
-		if (child->real_type == OBJ_OFS_DELTA) {
+		struct base_data result;
-			struct base_data result;
+
-			resolve_delta(child, base, &result);
+		assert(child->real_type == OBJ_OFS_DELTA);
-			if (i == ofs_last)
+		resolve_delta(child, base, &result);
-				free_base_data(base);
+		if (i == ofs_last)
-			find_unresolved_deltas(&result, base);
+			free_base_data(base);
-		}
+		find_unresolved_deltas(&result, base);
 	}
 
 	unlink_base_data(base);
@@ -584,7 +611,11 @@ static int compare_delta_entry(const void *a, const void *b)
 {
 	const struct delta_entry *delta_a = a;
 	const struct delta_entry *delta_b = b;
-	return memcmp(&delta_a->base, &delta_b->base, UNION_BASE_SZ);
+
+	/* group by type (ref vs ofs) and then by value (sha-1 or offset) */
+	return compare_delta_bases(&delta_a->base, &delta_b->base,
+				   objects[delta_a->obj_no].type,
+				   objects[delta_b->obj_no].type);
 }
 
 /* Parse all objects and return the pack content SHA1 hash */
@@ -608,7 +639,7 @@ static void parse_pack_objects(unsigned char *sha1)
 		struct object_entry *obj = &objects[i];
 		void *data = unpack_raw_entry(obj, &delta->base);
 		obj->real_type = obj->type;
-		if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
+		if (is_delta_type(obj->type)) {
 			nr_deltas++;
 			delta->obj_no = i;
 			delta++;
@@ -655,7 +686,7 @@ static void parse_pack_objects(unsigned char *sha1)
 		struct object_entry *obj = &objects[i];
 		struct base_data base_obj;
 
-		if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA)
+		if (is_delta_type(obj->type))
 			continue;
 		base_obj.obj = obj;
 		base_obj.data = NULL;
@@ -859,24 +890,137 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
 
 static int git_index_pack_config(const char *k, const char *v, void *cb)
 {
+	struct pack_idx_option *opts = cb;
+
 	if (!strcmp(k, "pack.indexversion")) {
-		pack_idx_default_version = git_config_int(k, v);
+		opts->version = git_config_int(k, v);
-		if (pack_idx_default_version > 2)
+		if (opts->version > 2)
-			die("bad pack.indexversion=%"PRIu32,
+			die("bad pack.indexversion=%"PRIu32, opts->version);
-				pack_idx_default_version);
 		return 0;
 	}
 	return git_default_config(k, v, cb);
 }
 
+static int cmp_uint32(const void *a_, const void *b_)
+{
+	uint32_t a = *((uint32_t *)a_);
+	uint32_t b = *((uint32_t *)b_);
+
+	return (a < b) ? -1 : (a != b);
+}
+
+static void read_v2_anomalous_offsets(struct packed_git *p,
+				      struct pack_idx_option *opts)
+{
+	const uint32_t *idx1, *idx2;
+	uint32_t i;
+
+	/* The address of the 4-byte offset table */
+	idx1 = (((const uint32_t *)p->index_data)
+		+ 2 /* 8-byte header */
+		+ 256 /* fan out */
+		+ 5 * p->num_objects /* 20-byte SHA-1 table */
+		+ p->num_objects /* CRC32 table */
+		);
+
+	/* The address of the 8-byte offset table */
+	idx2 = idx1 + p->num_objects;
+
+	for (i = 0; i < p->num_objects; i++) {
+		uint32_t off = ntohl(idx1[i]);
+		if (!(off & 0x80000000))
+			continue;
+		off = off & 0x7fffffff;
+		if (idx2[off * 2])
+			continue;
+		/*
+		 * The real offset is ntohl(idx2[off * 2]) in high 4
+		 * octets, and ntohl(idx2[off * 2 + 1]) in low 4
+		 * octets.  But idx2[off * 2] is Zero!!!
+		 */
+		ALLOC_GROW(opts->anomaly, opts->anomaly_nr + 1, opts->anomaly_alloc);
+		opts->anomaly[opts->anomaly_nr++] = ntohl(idx2[off * 2 + 1]);
+	}
+
+	if (1 < opts->anomaly_nr)
+		qsort(opts->anomaly, opts->anomaly_nr, sizeof(uint32_t), cmp_uint32);
+}
+
+static void read_idx_option(struct pack_idx_option *opts, const char *pack_name)
+{
+	struct packed_git *p = add_packed_git(pack_name, strlen(pack_name), 1);
+
+	if (!p)
+		die("Cannot open existing pack file '%s'", pack_name);
+	if (open_pack_index(p))
+		die("Cannot open existing pack idx file for '%s'", pack_name);
+
+	/* Read the attributes from the existing idx file */
+	opts->version = p->index_version;
+
+	if (opts->version == 2)
+		read_v2_anomalous_offsets(p, opts);
+
+	/*
+	 * Get rid of the idx file as we do not need it anymore.
+	 * NEEDSWORK: extract this bit from free_pack_by_name() in
+	 * sha1_file.c, perhaps?  It shouldn't matter very much as we
+	 * know we haven't installed this pack (hence we never have
+	 * read anything from it).
+	 */
+	close_pack_index(p);
+	free(p);
+}
+
+static void show_pack_info(int stat_only)
+{
+	int i, baseobjects = nr_objects - nr_deltas;
+	unsigned long *chain_histogram = NULL;
+
+	if (deepest_delta)
+		chain_histogram = xcalloc(deepest_delta, sizeof(unsigned long));
+
+	for (i = 0; i < nr_objects; i++) {
+		struct object_entry *obj = &objects[i];
+
+		if (is_delta_type(obj->type))
+			chain_histogram[obj->delta_depth - 1]++;
+		if (stat_only)
+			continue;
+		printf("%s %-6s %lu %lu %"PRIuMAX,
+		       sha1_to_hex(obj->idx.sha1),
+		       typename(obj->real_type), obj->size,
+		       (unsigned long)(obj[1].idx.offset - obj->idx.offset),
+		       (uintmax_t)obj->idx.offset);
+		if (is_delta_type(obj->type)) {
+			struct object_entry *bobj = &objects[obj->base_object_no];
+			printf(" %u %s", obj->delta_depth, sha1_to_hex(bobj->idx.sha1));
+		}
+		putchar('\n');
+	}
+
+	if (baseobjects)
+		printf("non delta: %d object%s\n",
+		       baseobjects, baseobjects > 1 ? "s" : "");
+	for (i = 0; i < deepest_delta; i++) {
+		if (!chain_histogram[i])
+			continue;
+		printf("chain length = %d: %lu object%s\n",
+		       i + 1,
+		       chain_histogram[i],
+		       chain_histogram[i] > 1 ? "s" : "");
+	}
+}
+
 int cmd_index_pack(int argc, const char **argv, const char *prefix)
 {
-	int i, fix_thin_pack = 0;
+	int i, fix_thin_pack = 0, verify = 0, stat_only = 0, stat = 0;
 	const char *curr_pack, *curr_index;
 	const char *index_name = NULL, *pack_name = NULL;
 	const char *keep_name = NULL, *keep_msg = NULL;
 	char *index_name_buf = NULL, *keep_name_buf = NULL;
 	struct pack_idx_entry **idx_objects;
+	struct pack_idx_option opts;
 	unsigned char pack_sha1[20];
 
 	if (argc == 2 && !strcmp(argv[1], "-h"))
@@ -884,7 +1028,8 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 
 	read_replace_refs = 0;
 
-	git_config(git_index_pack_config, NULL);
+	reset_pack_idx_option(&opts);
+	git_config(git_index_pack_config, &opts);
 	if (prefix && chdir(prefix))
 		die("Cannot come back to cwd");
 
@@ -898,6 +1043,15 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 				fix_thin_pack = 1;
 			} else if (!strcmp(arg, "--strict")) {
 				strict = 1;
+			} else if (!strcmp(arg, "--verify")) {
+				verify = 1;
+			} else if (!strcmp(arg, "--verify-stat")) {
+				verify = 1;
+				stat = 1;
+			} else if (!strcmp(arg, "--verify-stat-only")) {
+				verify = 1;
+				stat = 1;
+				stat_only = 1;
 			} else if (!strcmp(arg, "--keep")) {
 				keep_msg = "";
 			} else if (!prefixcmp(arg, "--keep=")) {
@@ -923,12 +1077,12 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 				index_name = argv[++i];
 			} else if (!prefixcmp(arg, "--index-version=")) {
 				char *c;
-				pack_idx_default_version = strtoul(arg + 16, &c, 10);
+				opts.version = strtoul(arg + 16, &c, 10);
-				if (pack_idx_default_version > 2)
+				if (opts.version > 2)
 					die("bad %s", arg);
 				if (*c == ',')
-					pack_idx_off32_limit = strtoul(c+1, &c, 0);
+					opts.off32_limit = strtoul(c+1, &c, 0);
-				if (*c || pack_idx_off32_limit & 0x80000000)
+				if (*c || opts.off32_limit & 0x80000000)
 					die("bad %s", arg);
 			} else
 				usage(index_pack_usage);
@@ -964,11 +1118,17 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 		strcpy(keep_name_buf + len - 5, ".keep");
 		keep_name = keep_name_buf;
 	}
+	if (verify) {
+		if (!index_name)
+			die("--verify with no packfile name given");
+		read_idx_option(&opts, index_name);
+		opts.flags |= WRITE_IDX_VERIFY;
+	}
 
 	curr_pack = open_pack_file(pack_name);
 	parse_pack_header();
-	objects = xmalloc((nr_objects + 1) * sizeof(struct object_entry));
+	objects = xcalloc(nr_objects + 1, sizeof(struct object_entry));
-	deltas = xmalloc(nr_objects * sizeof(struct delta_entry));
+	deltas = xcalloc(nr_objects, sizeof(struct delta_entry));
 	parse_pack_objects(pack_sha1);
 	if (nr_deltas == nr_resolved_deltas) {
 		stop_progress(&progress);
@@ -1008,16 +1168,22 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	if (strict)
 		check_objects();
 
+	if (stat)
+		show_pack_info(stat_only);
+
 	idx_objects = xmalloc((nr_objects) * sizeof(struct pack_idx_entry *));
 	for (i = 0; i < nr_objects; i++)
 		idx_objects[i] = &objects[i].idx;
-	curr_index = write_idx_file(index_name, idx_objects, nr_objects, pack_sha1);
+	curr_index = write_idx_file(index_name, idx_objects, nr_objects, &opts, pack_sha1);
 	free(idx_objects);
 
-	final(pack_name, curr_pack,
+	if (!verify)
-		index_name, curr_index,
+		final(pack_name, curr_pack,
-		keep_name, keep_msg,
+		      index_name, curr_index,
-		pack_sha1);
+		      keep_name, keep_msg,
+		      pack_sha1);
+	else
+		close(input_fd);
 	free(objects);
 	free(index_name_buf);
 	free(keep_name_buf);

builtin/pack-objects.c

@@ -70,6 +70,7 @@ static int local;
 static int incremental;
 static int ignore_packed_keep;
 static int allow_ofs_delta;
+static struct pack_idx_option pack_idx_opts;
 static const char *base_name;
 static int progress = 1;
 static int window = 10;
@@ -493,8 +494,8 @@ static void write_pack_file(void)
 			const char *idx_tmp_name;
 			char tmpname[PATH_MAX];
 
-			idx_tmp_name = write_idx_file(NULL, written_list,
+			idx_tmp_name = write_idx_file(NULL, written_list, nr_written,
-						      nr_written, sha1);
+						      &pack_idx_opts, sha1);
 
 			snprintf(tmpname, sizeof(tmpname), "%s-%s.pack",
 				 base_name, sha1_to_hex(sha1));
@@ -1884,10 +1885,10 @@ static int git_pack_config(const char *k, const char *v, void *cb)
 		return 0;
 	}
 	if (!strcmp(k, "pack.indexversion")) {
-		pack_idx_default_version = git_config_int(k, v);
+		pack_idx_opts.version = git_config_int(k, v);
-		if (pack_idx_default_version > 2)
+		if (pack_idx_opts.version > 2)
 			die("bad pack.indexversion=%"PRIu32,
-				pack_idx_default_version);
+			    pack_idx_opts.version);
 		return 0;
 	}
 	if (!strcmp(k, "pack.packsizelimit")) {
@@ -2134,6 +2135,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	rp_av[1] = "--objects"; /* --thin will make it --objects-edge */
 	rp_ac = 2;
 
+	reset_pack_idx_option(&pack_idx_opts);
 	git_config(git_pack_config, NULL);
 	if (!pack_compression_seen && core_compression_seen)
 		pack_compression_level = core_compression_level;
@@ -2278,12 +2280,12 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		}
 		if (!prefixcmp(arg, "--index-version=")) {
 			char *c;
-			pack_idx_default_version = strtoul(arg + 16, &c, 10);
+			pack_idx_opts.version = strtoul(arg + 16, &c, 10);
-			if (pack_idx_default_version > 2)
+			if (pack_idx_opts.version > 2)
 				die("bad %s", arg);
 			if (*c == ',')
-				pack_idx_off32_limit = strtoul(c+1, &c, 0);
+				pack_idx_opts.off32_limit = strtoul(c+1, &c, 0);
-			if (*c || pack_idx_off32_limit & 0x80000000)
+			if (*c || pack_idx_opts.off32_limit & 0x80000000)
 				die("bad %s", arg);
 			continue;
 		}

builtin/verify-pack.c

@@ -1,134 +1,53 @@
 #include "builtin.h"
 #include "cache.h"
-#include "pack.h"
+#include "run-command.h"
-#include "pack-revindex.h"
 #include "parse-options.h"
 
-#define MAX_CHAIN 50
-
 #define VERIFY_PACK_VERBOSE 01
 #define VERIFY_PACK_STAT_ONLY 02
 
-static void show_pack_info(struct packed_git *p, unsigned int flags)
-{
-	uint32_t nr_objects, i;
-	int cnt;
-	int stat_only = flags & VERIFY_PACK_STAT_ONLY;
-	unsigned long chain_histogram[MAX_CHAIN+1], baseobjects;
-
-	nr_objects = p->num_objects;
-	memset(chain_histogram, 0, sizeof(chain_histogram));
-	baseobjects = 0;
-
-	for (i = 0; i < nr_objects; i++) {
-		const unsigned char *sha1;
-		unsigned char base_sha1[20];
-		const char *type;
-		unsigned long size;
-		unsigned long store_size;
-		off_t offset;
-		unsigned int delta_chain_length;
-
-		sha1 = nth_packed_object_sha1(p, i);
-		if (!sha1)
-			die("internal error pack-check nth-packed-object");
-		offset = nth_packed_object_offset(p, i);
-		type = typename(packed_object_info_detail(p, offset, &size, &store_size,
-						 &delta_chain_length,
-						 base_sha1));
-		if (!stat_only)
-			printf("%s ", sha1_to_hex(sha1));
-		if (!delta_chain_length) {
-			if (!stat_only)
-				printf("%-6s %lu %lu %"PRIuMAX"\n",
-				       type, size, store_size, (uintmax_t)offset);
-			baseobjects++;
-		}
-		else {
-			if (!stat_only)
-				printf("%-6s %lu %lu %"PRIuMAX" %u %s\n",
-				       type, size, store_size, (uintmax_t)offset,
-				       delta_chain_length, sha1_to_hex(base_sha1));
-			if (delta_chain_length <= MAX_CHAIN)
-				chain_histogram[delta_chain_length]++;
-			else
-				chain_histogram[0]++;
-		}
-	}
-
-	if (baseobjects)
-		printf("non delta: %lu object%s\n",
-		       baseobjects, baseobjects > 1 ? "s" : "");
-
-	for (cnt = 1; cnt <= MAX_CHAIN; cnt++) {
-		if (!chain_histogram[cnt])
-			continue;
-		printf("chain length = %d: %lu object%s\n", cnt,
-		       chain_histogram[cnt],
-		       chain_histogram[cnt] > 1 ? "s" : "");
-	}
-	if (chain_histogram[0])
-		printf("chain length > %d: %lu object%s\n", MAX_CHAIN,
-		       chain_histogram[0],
-		       chain_histogram[0] > 1 ? "s" : "");
-}
-
 static int verify_one_pack(const char *path, unsigned int flags)
 {
-	char arg[PATH_MAX];
+	struct child_process index_pack;
-	int len;
+	const char *argv[] = {"index-pack", NULL, NULL, NULL };
+	struct strbuf arg = STRBUF_INIT;
 	int verbose = flags & VERIFY_PACK_VERBOSE;
 	int stat_only = flags & VERIFY_PACK_STAT_ONLY;
-	struct packed_git *pack;
 	int err;
 
-	len = strlcpy(arg, path, PATH_MAX);
+	if (stat_only)
-	if (len >= PATH_MAX)
+		argv[1] = "--verify-stat-only";
-		return error("name too long: %s", path);
+	else if (verbose)
-
+		argv[1] = "--verify-stat";
-	/*
-	 * In addition to "foo.idx" we accept "foo.pack" and "foo";
-	 * normalize these forms to "foo.idx" for add_packed_git().
-	 */
-	if (has_extension(arg, ".pack")) {
-		strcpy(arg + len - 5, ".idx");
-		len--;
-	} else if (!has_extension(arg, ".idx")) {
-		if (len + 4 >= PATH_MAX)
-			return error("name too long: %s.idx", arg);
-		strcpy(arg + len, ".idx");
-		len += 4;
-	}
-
-	/*
-	 * add_packed_git() uses our buffer (containing "foo.idx") to
-	 * build the pack filename ("foo.pack").  Make sure it fits.
-	 */
-	if (len + 1 >= PATH_MAX) {
-		arg[len - 4] = '\0';
-		return error("name too long: %s.pack", arg);
-	}
-
-	pack = add_packed_git(arg, len, 1);
-	if (!pack)
-		return error("packfile %s not found.", arg);
-
-	install_packed_git(pack);
-
-	if (!stat_only)
-		err = verify_pack(pack);
 	else
-		err = open_pack_index(pack);
+		argv[1] = "--verify";
+
+	/*
+	 * In addition to "foo.pack" we accept "foo.idx" and "foo";
+	 * normalize these forms to "foo.pack" for "index-pack --verify".
+	 */
+	strbuf_addstr(&arg, path);
+	if (has_extension(arg.buf, ".idx"))
+		strbuf_splice(&arg, arg.len - 3, 3, "pack", 4);
+	else if (!has_extension(arg.buf, ".pack"))
+		strbuf_add(&arg, ".pack", 5);
+	argv[2] = arg.buf;
+
+	memset(&index_pack, 0, sizeof(index_pack));
+	index_pack.argv = argv;
+	index_pack.git_cmd = 1;
+
+	err = run_command(&index_pack);
 
 	if (verbose || stat_only) {
 		if (err)
-			printf("%s: bad\n", pack->pack_name);
+			printf("%s: bad\n", arg.buf);
 		else {
-			show_pack_info(pack, flags);
 			if (!stat_only)
-				printf("%s: ok\n", pack->pack_name);
+				printf("%s: ok\n", arg.buf);
 		}
 	}
+	strbuf_release(&arg);
 
 	return err;
 }
@@ -159,7 +78,6 @@ int cmd_verify_pack(int argc, const char **argv, const char *prefix)
 	for (i = 0; i < argc; i++) {
 		if (verify_one_pack(argv[i], flags))
 			err = 1;
-		discard_revindex();
 	}
 
 	return err;

cache.h

@@ -1010,7 +1010,6 @@ extern off_t find_pack_entry_one(const unsigned char *, struct packed_git *);
 extern void *unpack_entry(struct packed_git *, off_t, enum object_type *, unsigned long *);
 extern unsigned long unpack_object_header_buffer(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep);
 extern unsigned long get_size_from_delta(struct packed_git *, struct pack_window **, off_t);
-extern int packed_object_info_detail(struct packed_git *, off_t, unsigned long *, unsigned long *, unsigned int *, unsigned char *);
 extern int unpack_object_header(struct packed_git *, struct pack_window **, off_t *, unsigned long *);
 
 struct object_info {

csum-file.c

@@ -11,8 +11,20 @@
 #include "progress.h"
 #include "csum-file.h"
 
-static void flush(struct sha1file *f, void * buf, unsigned int count)
+static void flush(struct sha1file *f, void *buf, unsigned int count)
 {
+	if (0 <= f->check_fd && count)  {
+		unsigned char check_buffer[8192];
+		ssize_t ret = read_in_full(f->check_fd, check_buffer, count);
+
+		if (ret < 0)
+			die_errno("%s: sha1 file read error", f->name);
+		if (ret < count)
+			die("%s: sha1 file truncated", f->name);
+		if (memcmp(buf, check_buffer, count))
+			die("sha1 file '%s' validation error", f->name);
+	}
+
 	for (;;) {
 		int ret = xwrite(f->fd, buf, count);
 		if (ret > 0) {
@@ -59,6 +71,17 @@ int sha1close(struct sha1file *f, unsigned char *result, unsigned int flags)
 		fd = 0;
 	} else
 		fd = f->fd;
+	if (0 <= f->check_fd) {
+		char discard;
+		int cnt = read_in_full(f->check_fd, &discard, 1);
+		if (cnt < 0)
+			die_errno("%s: error when reading the tail of sha1 file",
+				  f->name);
+		if (cnt)
+			die("%s: sha1 file has trailing garbage", f->name);
+		if (close(f->check_fd))
+			die_errno("%s: sha1 file error on close", f->name);
+	}
 	free(f);
 	return fd;
 }
@@ -101,10 +124,31 @@ struct sha1file *sha1fd(int fd, const char *name)
 	return sha1fd_throughput(fd, name, NULL);
 }
 
+struct sha1file *sha1fd_check(const char *name)
+{
+	int sink, check;
+	struct sha1file *f;
+
+	sink = open("/dev/null", O_WRONLY);
+	if (sink < 0)
+		return NULL;
+	check = open(name, O_RDONLY);
+	if (check < 0) {
+		int saved_errno = errno;
+		close(sink);
+		errno = saved_errno;
+		return NULL;
+	}
+	f = sha1fd(sink, name);
+	f->check_fd = check;
+	return f;
+}
+
 struct sha1file *sha1fd_throughput(int fd, const char *name, struct progress *tp)
 {
 	struct sha1file *f = xmalloc(sizeof(*f));
 	f->fd = fd;
+	f->check_fd = -1;
 	f->offset = 0;
 	f->total = 0;
 	f->tp = tp;

csum-file.h

@@ -6,6 +6,7 @@ struct progress;
 /* A SHA1-protected file */
 struct sha1file {
 	int fd;
+	int check_fd;
 	unsigned int offset;
 	git_SHA_CTX ctx;
 	off_t total;
@@ -21,6 +22,7 @@ struct sha1file {
 #define CSUM_FSYNC	2
 
 extern struct sha1file *sha1fd(int fd, const char *name);
+extern struct sha1file *sha1fd_check(const char *name);
 extern struct sha1file *sha1fd_throughput(int fd, const char *name, struct progress *tp);
 extern int sha1close(struct sha1file *, unsigned char *, unsigned int);
 extern int sha1write(struct sha1file *, void *, unsigned int);

fast-import.c

@@ -304,6 +304,7 @@ static unsigned int atom_cnt;
 static struct atom_str **atom_table;
 
 /* The .pack file being generated */
+static struct pack_idx_option pack_idx_opts;
 static unsigned int pack_id;
 static struct sha1file *pack_file;
 static struct packed_git *pack_data;
@@ -896,7 +897,7 @@ static const char *create_index(void)
 	if (c != last)
 		die("internal consistency error creating the index");
 
-	tmpfile = write_idx_file(NULL, idx, object_count, pack_data->sha1);
+	tmpfile = write_idx_file(NULL, idx, object_count, &pack_idx_opts, pack_data->sha1);
 	free(idx);
 	return tmpfile;
 }
@@ -3195,10 +3196,10 @@ static int git_pack_config(const char *k, const char *v, void *cb)
 		return 0;
 	}
 	if (!strcmp(k, "pack.indexversion")) {
-		pack_idx_default_version = git_config_int(k, v);
+		pack_idx_opts.version = git_config_int(k, v);
-		if (pack_idx_default_version > 2)
+		if (pack_idx_opts.version > 2)
 			die("bad pack.indexversion=%"PRIu32,
-			    pack_idx_default_version);
+			    pack_idx_opts.version);
 		return 0;
 	}
 	if (!strcmp(k, "pack.packsizelimit")) {
@@ -3252,6 +3253,7 @@ int main(int argc, const char **argv)
 		usage(fast_import_usage);
 
 	setup_git_directory();
+	reset_pack_idx_option(&pack_idx_opts);
 	git_config(git_pack_config, NULL);
 	if (!pack_compression_seen && core_compression_seen)
 		pack_compression_level = core_compression_level;

pack-write.c

@@ -2,8 +2,12 @@
 #include "pack.h"
 #include "csum-file.h"
 
-uint32_t pack_idx_default_version = 2;
+void reset_pack_idx_option(struct pack_idx_option *opts)
-uint32_t pack_idx_off32_limit = 0x7fffffff;
+{
+	memset(opts, 0, sizeof(*opts));
+	opts->version = 2;
+	opts->off32_limit = 0x7fffffff;
+}
 
 static int sha1_compare(const void *_a, const void *_b)
 {
@@ -12,13 +16,35 @@ static int sha1_compare(const void *_a, const void *_b)
 	return hashcmp(a->sha1, b->sha1);
 }
 
+static int cmp_uint32(const void *a_, const void *b_)
+{
+	uint32_t a = *((uint32_t *)a_);
+	uint32_t b = *((uint32_t *)b_);
+
+	return (a < b) ? -1 : (a != b);
+}
+
+static int need_large_offset(off_t offset, const struct pack_idx_option *opts)
+{
+	uint32_t ofsval;
+
+	if ((offset >> 31) || (opts->off32_limit < offset))
+		return 1;
+	if (!opts->anomaly_nr)
+		return 0;
+	ofsval = offset;
+	return !!bsearch(&ofsval, opts->anomaly, opts->anomaly_nr,
+			 sizeof(ofsval), cmp_uint32);
+}
+
 /*
  * On entry *sha1 contains the pack content SHA1 hash, on exit it is
  * the SHA1 hash of sorted object names. The objects array passed in
  * will be sorted by SHA1 on exit.
  */
 const char *write_idx_file(const char *index_name, struct pack_idx_entry **objects,
-			   int nr_objects, unsigned char *sha1)
+			   int nr_objects, const struct pack_idx_option *opts,
+			   unsigned char *sha1)
 {
 	struct sha1file *f;
 	struct pack_idx_entry **sorted_by_sha, **list, **last;
@@ -42,20 +68,25 @@ const char *write_idx_file(const char *index_name, struct pack_idx_entry **objec
 	else
 		sorted_by_sha = list = last = NULL;
 
-	if (!index_name) {
+	if (opts->flags & WRITE_IDX_VERIFY) {
-		static char tmpfile[PATH_MAX];
+		assert(index_name);
-		fd = odb_mkstemp(tmpfile, sizeof(tmpfile), "pack/tmp_idx_XXXXXX");
+		f = sha1fd_check(index_name);
-		index_name = xstrdup(tmpfile);
 	} else {
-		unlink(index_name);
+		if (!index_name) {
-		fd = open(index_name, O_CREAT|O_EXCL|O_WRONLY, 0600);
+			static char tmpfile[PATH_MAX];
+			fd = odb_mkstemp(tmpfile, sizeof(tmpfile), "pack/tmp_idx_XXXXXX");
+			index_name = xstrdup(tmpfile);
+		} else {
+			unlink(index_name);
+			fd = open(index_name, O_CREAT|O_EXCL|O_WRONLY, 0600);
+		}
+		if (fd < 0)
+			die_errno("unable to create '%s'", index_name);
+		f = sha1fd(fd, index_name);
 	}
-	if (fd < 0)
-		die_errno("unable to create '%s'", index_name);
-	f = sha1fd(fd, index_name);
 
 	/* if last object's offset is >= 2^31 we should use index V2 */
-	index_version = (last_obj_offset >> 31) ? 2 : pack_idx_default_version;
+	index_version = need_large_offset(last_obj_offset, opts) ? 2 : opts->version;
 
 	/* index versions 2 and above need a header */
 	if (index_version >= 2) {
@@ -115,8 +146,11 @@ const char *write_idx_file(const char *index_name, struct pack_idx_entry **objec
 		list = sorted_by_sha;
 		for (i = 0; i < nr_objects; i++) {
 			struct pack_idx_entry *obj = *list++;
-			uint32_t offset = (obj->offset <= pack_idx_off32_limit) ?
+			uint32_t offset;
-				obj->offset : (0x80000000 | nr_large_offset++);
+
+			offset = (need_large_offset(obj->offset, opts)
+				  ? (0x80000000 | nr_large_offset++)
+				  : obj->offset);
 			offset = htonl(offset);
 			sha1write(f, &offset, 4);
 		}
@@ -126,18 +160,20 @@ const char *write_idx_file(const char *index_name, struct pack_idx_entry **objec
 		while (nr_large_offset) {
 			struct pack_idx_entry *obj = *list++;
 			uint64_t offset = obj->offset;
-			if (offset > pack_idx_off32_limit) {
+			uint32_t split[2];
-				uint32_t split[2];
+
-				split[0] = htonl(offset >> 32);
+			if (!need_large_offset(offset, opts))
-				split[1] = htonl(offset & 0xffffffff);
+				continue;
-				sha1write(f, split, 8);
+			split[0] = htonl(offset >> 32);
-				nr_large_offset--;
+			split[1] = htonl(offset & 0xffffffff);
-			}
+			sha1write(f, split, 8);
+			nr_large_offset--;
 		}
 	}
 
 	sha1write(f, sha1, 20);
-	sha1close(f, NULL, CSUM_FSYNC);
+	sha1close(f, NULL, ((opts->flags & WRITE_IDX_VERIFY)
+			    ? CSUM_CLOSE : CSUM_FSYNC));
 	git_SHA1_Final(sha1, &ctx);
 	return index_name;
 }

pack.h

@@ -34,9 +34,24 @@ struct pack_header {
  */
 #define PACK_IDX_SIGNATURE 0xff744f63	/* "\377tOc" */
 
-/* These may be overridden by command-line parameters */
+struct pack_idx_option {
-extern uint32_t pack_idx_default_version;
+	unsigned flags;
-extern uint32_t pack_idx_off32_limit;
+	/* flag bits */
+#define WRITE_IDX_VERIFY 01
+
+	uint32_t version;
+	uint32_t off32_limit;
+
+	/*
+	 * List of offsets that would fit within off32_limit but
+	 * need to be written out as 64-bit entity for byte-for-byte
+	 * verification.
+	 */
+	int anomaly_alloc, anomaly_nr;
+	uint32_t *anomaly;
+};
+
+extern void reset_pack_idx_option(struct pack_idx_option *);
 
 /*
  * Packed object index header
@@ -55,7 +70,7 @@ struct pack_idx_entry {
 	off_t offset;
 };
 
-extern const char *write_idx_file(const char *index_name, struct pack_idx_entry **objects, int nr_objects, unsigned char *sha1);
+extern const char *write_idx_file(const char *index_name, struct pack_idx_entry **objects, int nr_objects, const struct pack_idx_option *, unsigned char *sha1);
 extern int check_pack_crc(struct packed_git *p, struct pack_window **w_curs, off_t offset, off_t len, unsigned int nr);
 extern int verify_pack_index(struct packed_git *);
 extern int verify_pack(struct packed_git *);

sha1_file.c

@@ -1553,61 +1553,6 @@ int unpack_object_header(struct packed_git *p,
 	return type;
 }
 
-int packed_object_info_detail(struct packed_git *p,
-				      off_t obj_offset,
-				      unsigned long *size,
-				      unsigned long *store_size,
-				      unsigned int *delta_chain_length,
-				      unsigned char *base_sha1)
-{
-	struct pack_window *w_curs = NULL;
-	off_t curpos;
-	unsigned long dummy;
-	unsigned char *next_sha1;
-	enum object_type type;
-	struct revindex_entry *revidx;
-
-	*delta_chain_length = 0;
-	curpos = obj_offset;
-	type = unpack_object_header(p, &w_curs, &curpos, size);
-
-	revidx = find_pack_revindex(p, obj_offset);
-	*store_size = revidx[1].offset - obj_offset;
-
-	for (;;) {
-		switch (type) {
-		default:
-			die("pack %s contains unknown object type %d",
-			    p->pack_name, type);
-		case OBJ_COMMIT:
-		case OBJ_TREE:
-		case OBJ_BLOB:
-		case OBJ_TAG:
-			unuse_pack(&w_curs);
-			return type;
-		case OBJ_OFS_DELTA:
-			obj_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset);
-			if (!obj_offset)
-				die("pack %s contains bad delta base reference of type %s",
-				    p->pack_name, typename(type));
-			if (*delta_chain_length == 0) {
-				revidx = find_pack_revindex(p, obj_offset);
-				hashcpy(base_sha1, nth_packed_object_sha1(p, revidx->nr));
-			}
-			break;
-		case OBJ_REF_DELTA:
-			next_sha1 = use_pack(p, &w_curs, curpos, NULL);
-			if (*delta_chain_length == 0)
-				hashcpy(base_sha1, next_sha1);
-			obj_offset = find_pack_entry_one(next_sha1, p);
-			break;
-		}
-		(*delta_chain_length)++;
-		curpos = obj_offset;
-		type = unpack_object_header(p, &w_curs, &curpos, &dummy);
-	}
-}
-
 static int packed_object_info(struct packed_git *p, off_t obj_offset,
 			      unsigned long *sizep, int *rtype)
 {

t/t5302-pack-index.sh

@@ -65,6 +65,14 @@ test_expect_success \
     'cmp "test-1-${pack1}.idx" "1.idx" &&
      cmp "test-2-${pack2}.idx" "2.idx"'
 
+test_expect_success 'index-pack --verify on index version 1' '
+	git index-pack --verify "test-1-${pack1}.pack"
+'
+
+test_expect_success 'index-pack --verify on index version 2' '
+	git index-pack --verify "test-2-${pack2}.pack"
+'
+
 test_expect_success \
     'index v2: force some 64-bit offsets with pack-objects' \
     'pack3=$(git pack-objects --index-version=2,0x40000 test-3 <obj-list)'
@@ -93,6 +101,16 @@ test_expect_success OFF64_T \
     '64-bit offsets: index-pack result should match pack-objects one' \
     'cmp "test-3-${pack3}.idx" "3.idx"'
 
+test_expect_success OFF64_T 'index-pack --verify on 64-bit offset v2 (cheat)' '
+	# This cheats by knowing which lower offset should still be encoded
+	# in 64-bit representation.
+	git index-pack --verify --index-version=2,0x40000 "test-3-${pack3}.pack"
+'
+
+test_expect_success OFF64_T 'index-pack --verify on 64-bit offset v2' '
+	git index-pack --verify "test-3-${pack3}.pack"
+'
+
 # returns the object number for given object in given pack index
 index_obj_nr()
 {
@@ -208,9 +226,8 @@ test_expect_success \
      ( while read obj
        do git cat-file -p $obj >/dev/null || exit 1
        done <obj-list ) &&
-     err=$(test_must_fail git verify-pack \
+     test_must_fail git verify-pack ".git/objects/pack/pack-${pack1}.pack"
-       ".git/objects/pack/pack-${pack1}.pack" 2>&1) &&
+'
-     echo "$err" | grep "CRC mismatch"'
 
 test_expect_success 'running index-pack in the object store' '
     rm -f .git/objects/pack/* &&