1 files changed, 269 insertions, 116 deletions

diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index b4cf8c53e0..98025da767 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -1,4 +1,4 @@
-#include "cache.h"
+#include "builtin.h"
 #include "delta.h"
 #include "pack.h"
 #include "csum-file.h"
@@ -11,15 +11,16 @@
 #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 object_entry {
 	struct pack_idx_entry idx;
 	unsigned long size;
 	unsigned int hdr_size;
 	enum object_type type;
 	enum object_type real_type;
+	unsigned delta_depth;
+	int base_object_no;
 };
 
 union delta_base {
@@ -44,8 +45,7 @@ struct base_data {
 #define FLAG_LINK (1u<<20)
 #define FLAG_CHECKED (1u<<21)
 
-struct delta_entry
-{
+struct delta_entry {
 	union delta_base base;
 	int obj_no;
 };
@@ -68,6 +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;
@@ -161,7 +162,7 @@ static void use(int bytes)
 	input_offset += bytes;
 
 	/* make sure off_t is sufficiently large not to wrap */
-	if (consumed_bytes > consumed_bytes + bytes)
+	if (signed_add_overflows(consumed_bytes, bytes))
 		die("pack too large for current definition of off_t");
 	consumed_bytes += bytes;
 }
@@ -209,7 +210,7 @@ static void parse_pack_header(void)
 static NORETURN void bad_object(unsigned long offset, const char *format,
 		       ...) __attribute__((format (printf, 2, 3)));
 
-static void bad_object(unsigned long offset, const char *format, ...)
+static NORETURN void bad_object(unsigned long offset, const char *format, ...)
 {
 	va_list params;
 	char buf[1024];
@@ -266,26 +267,23 @@ static void unlink_base_data(struct base_data *c)
 
 static void *unpack_entry_data(unsigned long offset, unsigned long size)
 {
-	z_stream stream;
+	int status;
+	git_zstream stream;
 	void *buf = xmalloc(size);
 
 	memset(&stream, 0, sizeof(stream));
+	git_inflate_init(&stream);
 	stream.next_out = buf;
 	stream.avail_out = size;
-	stream.next_in = fill(1);
-	stream.avail_in = input_len;
-	git_inflate_init(&stream);
 
-	for (;;) {
-		int ret = git_inflate(&stream, 0);
-		use(input_len - stream.avail_in);
-		if (stream.total_out == size && ret == Z_STREAM_END)
-			break;
-		if (ret != Z_OK)
-			bad_object(offset, "inflate returned %d", ret);
+	do {
 		stream.next_in = fill(1);
 		stream.avail_in = input_len;
-	}
+		status = git_inflate(&stream, 0);
+		use(input_len - stream.avail_in);
+	} while (status == Z_OK);
+	if (stream.total_out != size || status != Z_STREAM_END)
+		bad_object(offset, "inflate returned %d", status);
 	git_inflate_end(&stream);
 	return buf;
 }
@@ -299,7 +297,7 @@ static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_
 	void *data;
 
 	obj->idx.offset = consumed_bytes;
-	input_crc32 = crc32(0, Z_NULL, 0);
+	input_crc32 = crc32(0, NULL, 0);
 
 	p = fill(1);
 	c = *p;
@@ -359,38 +357,53 @@ static void *get_data_from_pack(struct object_entry *obj)
 {
 	off_t from = obj[0].idx.offset + obj[0].hdr_size;
 	unsigned long len = obj[1].idx.offset - from;
-	unsigned long rdy = 0;
-	unsigned char *src, *data;
-	z_stream stream;
-	int st;
+	unsigned char *data, *inbuf;
+	git_zstream stream;
+	int status;
 
-	src = xmalloc(len);
-	data = src;
-	do {
-		ssize_t n = pread(pack_fd, data + rdy, len - rdy, from + rdy);
-		if (n < 0)
-			die_errno("cannot pread pack file");
-		if (!n)
-			die("premature end of pack file, %lu bytes missing",
-			    len - rdy);
-		rdy += n;
-	} while (rdy < len);
 	data = xmalloc(obj->size);
+	inbuf = xmalloc((len < 64*1024) ? len : 64*1024);
+
 	memset(&stream, 0, sizeof(stream));
+	git_inflate_init(&stream);
 	stream.next_out = data;
 	stream.avail_out = obj->size;
-	stream.next_in = src;
-	stream.avail_in = len;
-	git_inflate_init(&stream);
-	while ((st = git_inflate(&stream, Z_FINISH)) == Z_OK);
-	git_inflate_end(&stream);
-	if (st != Z_STREAM_END || stream.total_out != obj->size)
+
+	do {
+		ssize_t n = (len < 64*1024) ? len : 64*1024;
+		n = pread(pack_fd, inbuf, n, from);
+		if (n < 0)
+			die_errno("cannot pread pack file");
+		if (!n)
+			die("premature end of pack file, %lu bytes missing", len);
+		from += n;
+		len -= n;
+		stream.next_in = inbuf;
+		stream.avail_in = n;
+		status = git_inflate(&stream, 0);
+	} while (len && status == Z_OK && !stream.avail_in);
+
+	/* This has been inflated OK when first encountered, so... */
+	if (status != Z_STREAM_END || stream.total_out != obj->size)
 		die("serious inflate inconsistency");
-	free(src);
+
+	git_inflate_end(&stream);
+	free(inbuf);
 	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;
 
@@ -399,7 +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) {
@@ -412,9 +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;
 
@@ -484,12 +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(
@@ -516,6 +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;
@@ -542,11 +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) {
@@ -558,24 +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;
-			resolve_delta(child, base, &result);
-			if (i == ref_last && ofs_last == -1)
-				free_base_data(base);
-			find_unresolved_deltas(&result, base);
-		}
+		struct base_data result;
+
+		assert(child->real_type == OBJ_REF_DELTA);
+		resolve_delta(child, base, &result);
+		if (i == ref_last && ofs_last == -1)
+			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;
-			resolve_delta(child, base, &result);
-			if (i == ofs_last)
-				free_base_data(base);
-			find_unresolved_deltas(&result, base);
-		}
+		struct base_data result;
+
+		assert(child->real_type == OBJ_OFS_DELTA);
+		resolve_delta(child, base, &result);
+		if (i == ofs_last)
+			free_base_data(base);
+		find_unresolved_deltas(&result, base);
 	}
 
 	unlink_base_data(base);
@@ -585,7 +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 */
@@ -609,7 +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++;
@@ -656,7 +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;
@@ -667,26 +697,26 @@ static void parse_pack_objects(unsigned char *sha1)
 
 static int write_compressed(struct sha1file *f, void *in, unsigned int size)
 {
-	z_stream stream;
-	unsigned long maxsize;
-	void *out;
+	git_zstream stream;
+	int status;
+	unsigned char outbuf[4096];
 
 	memset(&stream, 0, sizeof(stream));
-	deflateInit(&stream, zlib_compression_level);
-	maxsize = deflateBound(&stream, size);
-	out = xmalloc(maxsize);
-
-	/* Compress it */
+	git_deflate_init(&stream, zlib_compression_level);
 	stream.next_in = in;
 	stream.avail_in = size;
-	stream.next_out = out;
-	stream.avail_out = maxsize;
-	while (deflate(&stream, Z_FINISH) == Z_OK);
-	deflateEnd(&stream);
 
+	do {
+		stream.next_out = outbuf;
+		stream.avail_out = sizeof(outbuf);
+		status = git_deflate(&stream, Z_FINISH);
+		sha1write(f, outbuf, sizeof(outbuf) - stream.avail_out);
+	} while (status == Z_OK);
+
+	if (status != Z_STREAM_END)
+		die("unable to deflate appended object (%d)", status);
 	size = stream.total_out;
-	sha1write(f, out, size);
-	free(out);
+	git_deflate_end(&stream);
 	return size;
 }
 
@@ -860,48 +890,148 @@ 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);
-		if (pack_idx_default_version > 2)
-			die("bad pack.indexversion=%"PRIu32,
-				pack_idx_default_version);
+		opts->version = git_config_int(k, v);
+		if (opts->version > 2)
+			die("bad pack.indexversion=%"PRIu32, opts->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"))
 		usage(index_pack_usage);
 
-	/*
-	 * We wish to read the repository's config file if any, and
-	 * for that it is necessary to call setup_git_directory_gently().
-	 * However if the cwd was inside .git/objects/pack/ then we need
-	 * to go back there or all the pack name arguments will be wrong.
-	 * And in that case we cannot rely on any prefix returned by
-	 * setup_git_directory_gently() either.
-	 */
-	{
-		char cwd[PATH_MAX+1];
-		int nongit;
-
-		if (!getcwd(cwd, sizeof(cwd)-1))
-			die("Unable to get current working directory");
-		setup_git_directory_gently(&nongit);
-		git_config(git_index_pack_config, NULL);
-		if (chdir(cwd))
-			die("Cannot come back to cwd");
-	}
+	read_replace_refs = 0;
+
+	reset_pack_idx_option(&opts);
+	git_config(git_index_pack_config, &opts);
+	if (prefix && chdir(prefix))
+		die("Cannot come back to cwd");
 
 	for (i = 1; i < argc; i++) {
 		const char *arg = argv[i];
@@ -913,6 +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=")) {
@@ -938,12 +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);
-				if (pack_idx_default_version > 2)
+				opts.version = strtoul(arg + 16, &c, 10);
+				if (opts.version > 2)
 					die("bad %s", arg);
 				if (*c == ',')
-					pack_idx_off32_limit = strtoul(c+1, &c, 0);
-				if (*c || pack_idx_off32_limit & 0x80000000)
+					opts.off32_limit = strtoul(c+1, &c, 0);
+				if (*c || opts.off32_limit & 0x80000000)
 					die("bad %s", arg);
 			} else
 				usage(index_pack_usage);
@@ -979,11 +1118,19 @@ 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 | WRITE_IDX_STRICT;
+	}
+	if (strict)
+		opts.flags |= WRITE_IDX_STRICT;
 
 	curr_pack = open_pack_file(pack_name);
 	parse_pack_header();
-	objects = xmalloc((nr_objects + 1) * sizeof(struct object_entry));
-	deltas = xmalloc(nr_objects * sizeof(struct delta_entry));
+	objects = xcalloc(nr_objects + 1, sizeof(struct object_entry));
+	deltas = xcalloc(nr_objects, sizeof(struct delta_entry));
 	parse_pack_objects(pack_sha1);
 	if (nr_deltas == nr_resolved_deltas) {
 		stop_progress(&progress);
@@ -1023,16 +1170,22 @@ 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,
-		index_name, curr_index,
-		keep_name, keep_msg,
-		pack_sha1);
+	if (!verify)
+		final(pack_name, curr_pack,
+		      index_name, curr_index,
+		      keep_name, keep_msg,
+		      pack_sha1);
+	else
+		close(input_fd);
 	free(objects);
 	free(index_name_buf);
 	free(keep_name_buf);