struct object_entry
{
- unsigned long offset;
+ off_t offset;
unsigned long size;
unsigned int hdr_size;
+ uint32_t crc32;
enum object_type type;
enum object_type real_type;
unsigned char sha1[20];
union delta_base {
unsigned char sha1[20];
- unsigned long offset;
+ off_t offset;
};
/*
/* We always read in 4kB chunks. */
static unsigned char input_buffer[4096];
-static unsigned long input_offset, input_len, consumed_bytes;
+static unsigned int input_offset, input_len;
+static off_t consumed_bytes;
static SHA_CTX input_ctx;
+static uint32_t input_crc32;
static int input_fd, output_fd, pack_fd;
/* Discard current buffer used content. */
{
if (bytes > input_len)
die("used more bytes than were available");
+ input_crc32 = crc32(input_crc32, input_buffer + input_offset, bytes);
input_len -= bytes;
input_offset += bytes;
+
+ /* make sure off_t is sufficiently large not to wrap */
+ if (consumed_bytes > consumed_bytes + bytes)
+ die("pack too large for current definition of off_t");
consumed_bytes += bytes;
}
if (!pack_name) {
static char tmpfile[PATH_MAX];
snprintf(tmpfile, sizeof(tmpfile),
- "%s/pack_XXXXXX", get_object_directory());
+ "%s/tmp_pack_XXXXXX", get_object_directory());
output_fd = mkstemp(tmpfile);
pack_name = xstrdup(tmpfile);
} else
static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_base)
{
unsigned char *p, c;
- unsigned long size, base_offset;
+ unsigned long size;
+ off_t base_offset;
unsigned shift;
+ void *data;
obj->offset = consumed_bytes;
+ input_crc32 = crc32(0, Z_NULL, 0);
p = fill(1);
c = *p;
base_offset = c & 127;
while (c & 128) {
base_offset += 1;
- if (!base_offset || base_offset & ~(~0UL >> 7))
+ if (!base_offset || MSB(base_offset, 7))
bad_object(obj->offset, "offset value overflow for delta base object");
p = fill(1);
c = *p;
}
obj->hdr_size = consumed_bytes - obj->offset;
- return unpack_entry_data(obj->offset, obj->size);
+ data = unpack_entry_data(obj->offset, obj->size);
+ obj->crc32 = input_crc32;
+ return data;
}
static void *get_data_from_pack(struct object_entry *obj)
static void sha1_object(const void *data, unsigned long size,
enum object_type type, unsigned char *sha1)
{
- SHA_CTX ctx;
- char header[50];
- int header_size;
- const char *type_str;
-
- switch (type) {
- case OBJ_COMMIT: type_str = commit_type; break;
- case OBJ_TREE: type_str = tree_type; break;
- case OBJ_BLOB: type_str = blob_type; break;
- case OBJ_TAG: type_str = tag_type; break;
- default:
- die("bad type %d", type);
+ hash_sha1_file(data, size, typename(type), sha1);
+ if (has_sha1_file(sha1)) {
+ void *has_data;
+ enum object_type has_type;
+ unsigned long has_size;
+ has_data = read_sha1_file(sha1, &has_type, &has_size);
+ if (!has_data)
+ die("cannot read existing object %s", sha1_to_hex(sha1));
+ if (size != has_size || type != has_type ||
+ memcmp(data, has_data, size) != 0)
+ die("SHA1 COLLISION FOUND WITH %s !", sha1_to_hex(sha1));
+ free(has_data);
}
-
- header_size = sprintf(header, "%s %lu", type_str, size) + 1;
-
- SHA1_Init(&ctx);
- SHA1_Update(&ctx, header, header_size);
- SHA1_Update(&ctx, data, size);
- SHA1_Final(sha1, &ctx);
}
static void resolve_delta(struct object_entry *delta_obj, void *base_data,
fputc('\n', stderr);
}
-static int write_compressed(int fd, void *in, unsigned int size)
+static int write_compressed(int fd, void *in, unsigned int size, uint32_t *obj_crc)
{
z_stream stream;
unsigned long maxsize;
size = stream.total_out;
write_or_die(fd, out, size);
+ *obj_crc = crc32(*obj_crc, out, size);
free(out);
return size;
}
-static void append_obj_to_pack(void *buf,
+static void append_obj_to_pack(const unsigned char *sha1, void *buf,
unsigned long size, enum object_type type)
{
struct object_entry *obj = &objects[nr_objects++];
}
header[n++] = c;
write_or_die(output_fd, header, n);
+ obj[0].crc32 = crc32(0, Z_NULL, 0);
+ obj[0].crc32 = crc32(obj[0].crc32, header, n);
obj[1].offset = obj[0].offset + n;
- obj[1].offset += write_compressed(output_fd, buf, size);
- sha1_object(buf, size, type, obj->sha1);
+ obj[1].offset += write_compressed(output_fd, buf, size, &obj[0].crc32);
+ hashcpy(obj->sha1, sha1);
}
static int delta_pos_compare(const void *_a, const void *_b)
resolve_delta(child, data, size, type);
}
- append_obj_to_pack(data, size, type);
+ if (check_sha1_signature(d->base.sha1, data, size, typename(type)))
+ die("local object %s is corrupt", sha1_to_hex(d->base.sha1));
+ append_obj_to_pack(d->base.sha1, data, size, type);
free(data);
if (verbose)
percent = display_progress(nr_resolved_deltas,
write_or_die(output_fd, sha1, 20);
}
+static uint32_t index_default_version = 1;
+static uint32_t index_off32_limit = 0x7fffffff;
+
static int sha1_compare(const void *_a, const void *_b)
{
struct object_entry *a = *(struct object_entry **)_a;
{
struct sha1file *f;
struct object_entry **sorted_by_sha, **list, **last;
- unsigned int array[256];
+ uint32_t array[256];
int i, fd;
SHA_CTX ctx;
+ uint32_t index_version;
if (nr_objects) {
sorted_by_sha =
sorted_by_sha[i] = &objects[i];
qsort(sorted_by_sha, nr_objects, sizeof(sorted_by_sha[0]),
sha1_compare);
-
}
else
sorted_by_sha = list = last = NULL;
if (!index_name) {
static char tmpfile[PATH_MAX];
snprintf(tmpfile, sizeof(tmpfile),
- "%s/index_XXXXXX", get_object_directory());
+ "%s/tmp_idx_XXXXXX", get_object_directory());
fd = mkstemp(tmpfile);
index_name = xstrdup(tmpfile);
} else {
die("unable to create %s: %s", index_name, strerror(errno));
f = sha1fd(fd, index_name);
+ /* if last object's offset is >= 2^31 we should use index V2 */
+ index_version = (objects[nr_objects-1].offset >> 31) ? 2 : index_default_version;
+
+ /* index versions 2 and above need a header */
+ if (index_version >= 2) {
+ struct pack_idx_header hdr;
+ hdr.idx_signature = htonl(PACK_IDX_SIGNATURE);
+ hdr.idx_version = htonl(index_version);
+ sha1write(f, &hdr, sizeof(hdr));
+ }
+
/*
* Write the first-level table (the list is sorted,
* but we use a 256-entry lookup to be able to avoid
array[i] = htonl(next - sorted_by_sha);
list = next;
}
- sha1write(f, array, 256 * sizeof(int));
+ sha1write(f, array, 256 * 4);
- /* recompute the SHA1 hash of sorted object names.
- * currently pack-objects does not do this, but that
- * can be fixed.
- */
+ /* compute the SHA1 hash of sorted object names. */
SHA1_Init(&ctx);
+
/*
* Write the actual SHA1 entries..
*/
list = sorted_by_sha;
for (i = 0; i < nr_objects; i++) {
struct object_entry *obj = *list++;
- unsigned int offset = htonl(obj->offset);
- sha1write(f, &offset, 4);
+ if (index_version < 2) {
+ uint32_t offset = htonl(obj->offset);
+ sha1write(f, &offset, 4);
+ }
sha1write(f, obj->sha1, 20);
SHA1_Update(&ctx, obj->sha1, 20);
}
+
+ if (index_version >= 2) {
+ unsigned int nr_large_offset = 0;
+
+ /* write the crc32 table */
+ list = sorted_by_sha;
+ for (i = 0; i < nr_objects; i++) {
+ struct object_entry *obj = *list++;
+ uint32_t crc32_val = htonl(obj->crc32);
+ sha1write(f, &crc32_val, 4);
+ }
+
+ /* write the 32-bit offset table */
+ list = sorted_by_sha;
+ for (i = 0; i < nr_objects; i++) {
+ struct object_entry *obj = *list++;
+ uint32_t offset = (obj->offset <= index_off32_limit) ?
+ obj->offset : (0x80000000 | nr_large_offset++);
+ offset = htonl(offset);
+ sha1write(f, &offset, 4);
+ }
+
+ /* write the large offset table */
+ list = sorted_by_sha;
+ while (nr_large_offset) {
+ struct object_entry *obj = *list++;
+ uint64_t offset = obj->offset;
+ if (offset > index_off32_limit) {
+ uint32_t split[2];
+ split[0] = htonl(offset >> 32);
+ split[1] = htonl(offset & 0xffffffff);
+ sha1write(f, split, 8);
+ nr_large_offset--;
+ }
+ }
+ }
+
sha1write(f, sha1, 20);
sha1close(f, NULL, 1);
free(sorted_by_sha);
const char *keep_name, const char *keep_msg,
unsigned char *sha1)
{
- char *report = "pack";
+ const char *report = "pack";
char name[PATH_MAX];
int err;
if (index_name || (i+1) >= argc)
usage(index_pack_usage);
index_name = argv[++i];
+ } else if (!prefixcmp(arg, "--index-version=")) {
+ char *c;
+ index_default_version = strtoul(arg + 16, &c, 10);
+ if (index_default_version > 2)
+ die("bad %s", arg);
+ if (*c == ',')
+ index_off32_limit = strtoul(c+1, &c, 0);
+ if (*c || index_off32_limit & 0x80000000)
+ die("bad %s", arg);
} else
usage(index_pack_usage);
continue;