int st;
memset(&stream, 0, sizeof(stream));
- inflateInit(&stream);
+ git_inflate_init(&stream);
do {
in = use_pack(p, w_curs, offset, &stream.avail_in);
stream.next_in = in;
stream.next_out = fakebuf;
stream.avail_out = sizeof(fakebuf);
- st = inflate(&stream, Z_FINISH);
+ st = git_inflate(&stream, Z_FINISH);
offset += stream.next_in - in;
} while (st == Z_OK || st == Z_BUF_ERROR);
- inflateEnd(&stream);
+ git_inflate_end(&stream);
return (st == Z_STREAM_END &&
stream.total_out == expect &&
stream.total_in == len) ? 0 : -1;
*/
if (!to_reuse) {
+ no_reuse:
if (!usable_delta) {
buf = read_sha1_file(entry->idx.sha1, &type, &size);
if (!buf)
struct revindex_entry *revidx;
off_t offset;
- if (entry->delta) {
+ if (entry->delta)
type = (allow_ofs_delta && entry->delta->idx.offset) ?
OBJ_OFS_DELTA : OBJ_REF_DELTA;
- reused_delta++;
- }
hdrlen = encode_header(type, entry->size, header);
+
offset = entry->in_pack_offset;
revidx = find_pack_revindex(p, offset);
datalen = revidx[1].offset - offset;
if (!pack_to_stdout && p->index_version > 1 &&
- check_pack_crc(p, &w_curs, offset, datalen, revidx->nr))
- die("bad packed object CRC for %s", sha1_to_hex(entry->idx.sha1));
+ check_pack_crc(p, &w_curs, offset, datalen, revidx->nr)) {
+ error("bad packed object CRC for %s", sha1_to_hex(entry->idx.sha1));
+ unuse_pack(&w_curs);
+ goto no_reuse;
+ }
+
offset += entry->in_pack_header_size;
datalen -= entry->in_pack_header_size;
+ if (!pack_to_stdout && p->index_version == 1 &&
+ check_pack_inflate(p, &w_curs, offset, datalen, entry->size)) {
+ error("corrupt packed object for %s", sha1_to_hex(entry->idx.sha1));
+ unuse_pack(&w_curs);
+ goto no_reuse;
+ }
+
if (type == OBJ_OFS_DELTA) {
off_t ofs = entry->idx.offset - entry->delta->idx.offset;
unsigned pos = sizeof(dheader) - 1;
dheader[pos] = ofs & 127;
while (ofs >>= 7)
dheader[--pos] = 128 | (--ofs & 127);
- if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit)
+ if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) {
+ unuse_pack(&w_curs);
return 0;
+ }
sha1write(f, header, hdrlen);
sha1write(f, dheader + pos, sizeof(dheader) - pos);
hdrlen += sizeof(dheader) - pos;
+ reused_delta++;
} else if (type == OBJ_REF_DELTA) {
- if (limit && hdrlen + 20 + datalen + 20 >= limit)
+ if (limit && hdrlen + 20 + datalen + 20 >= limit) {
+ unuse_pack(&w_curs);
return 0;
+ }
sha1write(f, header, hdrlen);
sha1write(f, entry->delta->idx.sha1, 20);
hdrlen += 20;
+ reused_delta++;
} else {
- if (limit && hdrlen + datalen + 20 >= limit)
+ if (limit && hdrlen + datalen + 20 >= limit) {
+ unuse_pack(&w_curs);
return 0;
+ }
sha1write(f, header, hdrlen);
}
-
- if (!pack_to_stdout && p->index_version == 1 &&
- check_pack_inflate(p, &w_curs, offset, datalen, entry->size))
- die("corrupt packed object for %s", sha1_to_hex(entry->idx.sha1));
copy_pack_data(f, p, &w_curs, offset, datalen);
unuse_pack(&w_curs);
reused++;
} else {
char tmpname[PATH_MAX];
int fd;
- snprintf(tmpname, sizeof(tmpname),
- "%s/pack/tmp_pack_XXXXXX", get_object_directory());
- fd = xmkstemp(tmpname);
+ fd = odb_mkstemp(tmpname, sizeof(tmpname),
+ "pack/tmp_pack_XXXXXX");
pack_tmp_name = xstrdup(tmpname);
f = sha1fd(fd, pack_tmp_name);
}
* We want in_pack_type even if we do not reuse delta
* since non-delta representations could still be reused.
*/
- used = unpack_object_header_gently(buf, avail,
+ used = unpack_object_header_buffer(buf, avail,
&entry->in_pack_type,
&entry->size);
+ if (used == 0)
+ goto give_up;
/*
* Determine if this is a delta and if so whether we can
/* Not a delta hence we've already got all we need. */
entry->type = entry->in_pack_type;
entry->in_pack_header_size = used;
+ if (entry->type < OBJ_COMMIT || entry->type > OBJ_BLOB)
+ goto give_up;
unuse_pack(&w_curs);
return;
case OBJ_REF_DELTA:
ofs = c & 127;
while (c & 128) {
ofs += 1;
- if (!ofs || MSB(ofs, 7))
- die("delta base offset overflow in pack for %s",
- sha1_to_hex(entry->idx.sha1));
+ if (!ofs || MSB(ofs, 7)) {
+ error("delta base offset overflow in pack for %s",
+ sha1_to_hex(entry->idx.sha1));
+ goto give_up;
+ }
c = buf[used_0++];
ofs = (ofs << 7) + (c & 127);
}
- if (ofs >= entry->in_pack_offset)
- die("delta base offset out of bound for %s",
- sha1_to_hex(entry->idx.sha1));
ofs = entry->in_pack_offset - ofs;
+ if (ofs <= 0 || ofs >= entry->in_pack_offset) {
+ error("delta base offset out of bound for %s",
+ sha1_to_hex(entry->idx.sha1));
+ goto give_up;
+ }
if (reuse_delta && !entry->preferred_base) {
struct revindex_entry *revidx;
revidx = find_pack_revindex(p, ofs);
+ if (!revidx)
+ goto give_up;
base_ref = nth_packed_object_sha1(p, revidx->nr);
}
entry->in_pack_header_size = used + used_0;
*/
entry->type = entry->in_pack_type;
entry->delta = base_entry;
+ entry->delta_size = entry->size;
entry->delta_sibling = base_entry->delta_child;
base_entry->delta_child = entry;
unuse_pack(&w_curs);
*/
entry->size = get_size_from_delta(p, &w_curs,
entry->in_pack_offset + entry->in_pack_header_size);
+ if (entry->size == 0)
+ goto give_up;
unuse_pack(&w_curs);
return;
}
* with sha1_object_info() to find about the object type
* at this point...
*/
+ give_up:
unuse_pack(&w_curs);
}
max_size = trg_entry->delta_size;
ref_depth = trg->depth;
}
- max_size = max_size * (max_depth - src->depth) /
+ max_size = (uint64_t)max_size * (max_depth - src->depth) /
(max_depth - ref_depth + 1);
if (max_size == 0)
return 0;
int window, int depth, unsigned *processed)
{
uint32_t i, idx = 0, count = 0;
- unsigned int array_size = window * sizeof(struct unpacked);
struct unpacked *array;
unsigned long mem_usage = 0;
- array = xmalloc(array_size);
- memset(array, 0, array_size);
+ array = xcalloc(window, sizeof(struct unpacked));
for (;;) {
struct object_entry *entry;
get_object_details();
+ /*
+ * If we're locally repacking then we need to be doubly careful
+ * from now on in order to make sure no stealth corruption gets
+ * propagated to the new pack. Clients receiving streamed packs
+ * should validate everything they get anyway so no need to incur
+ * the additional cost here in that case.
+ */
+ if (!pack_to_stdout)
+ do_check_packed_object_crc = 1;
+
if (!nr_objects || !window || !depth)
return;
if (entry->type < 0)
die("unable to get type of object %s",
sha1_to_hex(entry->idx.sha1));
+ } else {
+ if (entry->type < 0) {
+ /*
+ * This object is not found, but we
+ * don't have to include it anyway.
+ */
+ continue;
+ }
}
delta_list[n++] = entry;
pos = strchr(pos, '/');
if (!pos)
break;
- *pos = 0;
+ while (*++pos == '/')
+ ;
+ if (!*pos)
+ break;
+ *--pos = '\0';
if (!stat(path, &st)) {
/* path exists */
if (!S_ISDIR(st.st_mode)) {
*/
static int link_alt_odb_entry(const char * entry, int len, const char * relative_base, int depth)
{
- struct stat st;
const char *objdir = get_object_directory();
struct alternate_object_database *ent;
struct alternate_object_database *alt;
ent->base[pfxlen] = ent->base[entlen-1] = 0;
/* Detect cases where alternate disappeared */
- if (stat(ent->base, &st) || !S_ISDIR(st.st_mode)) {
+ if (!is_directory(ent->base)) {
error("object directory %s does not exist; "
"check .git/objects/info/alternates.",
ent->base);
link_alt_odb_entries(alt, alt + strlen(alt), '\n', NULL, 0);
}
+void foreach_alt_odb(alt_odb_fn fn, void *cb)
+{
+ struct alternate_object_database *ent;
+
+ prepare_alt_odb();
+ for (ent = alt_odb_list; ent; ent = ent->next)
+ if (fn(ent, cb))
+ return;
+}
+
void prepare_alt_odb(void)
{
const char *alt;
return 0;
}
-unsigned long unpack_object_header_gently(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep)
+unsigned long unpack_object_header_buffer(const unsigned char *buf,
+ unsigned long len, enum object_type *type, unsigned long *sizep)
{
unsigned shift;
unsigned char c;
size = c & 15;
shift = 4;
while (c & 0x80) {
- if (len <= used)
- return 0;
- if (sizeof(long) * 8 <= shift)
+ if (len <= used || sizeof(long) * 8 <= shift) {
+ error("bad object header");
return 0;
+ }
c = buf[used++];
size += (c & 0x7f) << shift;
shift += 7;
stream->avail_out = bufsiz;
if (legacy_loose_object(map)) {
- inflateInit(stream);
- return inflate(stream, 0);
+ git_inflate_init(stream);
+ return git_inflate(stream, 0);
}
* really worth it and we don't write it any longer. But we
* can still read it.
*/
- used = unpack_object_header_gently(map, mapsize, &type, &size);
+ used = unpack_object_header_buffer(map, mapsize, &type, &size);
if (!used || !valid_loose_object_type[type])
return -1;
map += used;
/* Set up the stream for the rest.. */
stream->next_in = map;
stream->avail_in = mapsize;
- inflateInit(stream);
+ git_inflate_init(stream);
/* And generate the fake traditional header */
stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
stream->next_out = buf + bytes;
stream->avail_out = size - bytes;
while (status == Z_OK)
- status = inflate(stream, Z_FINISH);
+ status = git_inflate(stream, Z_FINISH);
}
buf[size] = 0;
if (status == Z_STREAM_END && !stream->avail_in) {
- inflateEnd(stream);
+ git_inflate_end(stream);
return buf;
}
stream.next_out = delta_head;
stream.avail_out = sizeof(delta_head);
- inflateInit(&stream);
+ git_inflate_init(&stream);
do {
in = use_pack(p, w_curs, curpos, &stream.avail_in);
stream.next_in = in;
- st = inflate(&stream, Z_FINISH);
+ st = git_inflate(&stream, Z_FINISH);
curpos += stream.next_in - in;
} while ((st == Z_OK || st == Z_BUF_ERROR) &&
stream.total_out < sizeof(delta_head));
- inflateEnd(&stream);
- if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head))
- die("delta data unpack-initial failed");
+ git_inflate_end(&stream);
+ if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) {
+ error("delta data unpack-initial failed");
+ return 0;
+ }
/* Examine the initial part of the delta to figure out
* the result size.
base_offset = (base_offset << 7) + (c & 127);
}
base_offset = delta_obj_offset - base_offset;
- if (base_offset >= delta_obj_offset)
+ if (base_offset <= 0 || base_offset >= delta_obj_offset)
return 0; /* out of bound */
*curpos += used;
} else if (type == OBJ_REF_DELTA) {
off_t base_offset;
base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset);
+ if (!base_offset)
+ return OBJ_BAD;
type = packed_object_info(p, base_offset, NULL);
+ if (type <= OBJ_NONE) {
+ struct revindex_entry *revidx;
+ const unsigned char *base_sha1;
+ revidx = find_pack_revindex(p, base_offset);
+ if (!revidx)
+ return OBJ_BAD;
+ base_sha1 = nth_packed_object_sha1(p, revidx->nr);
+ mark_bad_packed_object(p, base_sha1);
+ type = sha1_object_info(base_sha1, NULL);
+ if (type <= OBJ_NONE)
+ return OBJ_BAD;
+ }
/* We choose to only get the type of the base object and
* ignore potentially corrupt pack file that expects the delta
* based on a base with a wrong size. This saves tons of
* inflate() calls.
*/
- if (sizep)
+ if (sizep) {
*sizep = get_size_from_delta(p, w_curs, curpos);
+ if (*sizep == 0)
+ type = OBJ_BAD;
+ }
return type;
}
* insane, so we know won't exceed what we have been given.
*/
base = use_pack(p, w_curs, *curpos, &left);
- used = unpack_object_header_gently(base, left, &type, sizep);
- if (!used)
- die("object offset outside of pack file");
- *curpos += used;
+ used = unpack_object_header_buffer(base, left, &type, sizep);
+ if (!used) {
+ type = OBJ_BAD;
+ } else
+ *curpos += used;
return type;
}
*sizep = size;
break;
default:
- die("pack %s contains unknown object type %d",
- p->pack_name, type);
+ error("unknown object type %i at offset %"PRIuMAX" in %s",
+ type, (uintmax_t)obj_offset, p->pack_name);
+ type = OBJ_BAD;
}
unuse_pack(&w_curs);
return type;
stream.next_out = buffer;
stream.avail_out = size;
- inflateInit(&stream);
+ git_inflate_init(&stream);
do {
in = use_pack(p, w_curs, curpos, &stream.avail_in);
stream.next_in = in;
- st = inflate(&stream, Z_FINISH);
+ st = git_inflate(&stream, Z_FINISH);
curpos += stream.next_in - in;
} while (st == Z_OK || st == Z_BUF_ERROR);
- inflateEnd(&stream);
+ git_inflate_end(&stream);
if ((st != Z_STREAM_END) || stream.total_out != size) {
free(buffer);
return NULL;
struct delta_base_cache_entry *ent = delta_base_cache + hash;
ret = ent->data;
- if (ret && ent->p == p && ent->base_offset == base_offset)
- goto found_cache_entry;
- return unpack_entry(p, base_offset, type, base_size);
+ if (!ret || ent->p != p || ent->base_offset != base_offset)
+ return unpack_entry(p, base_offset, type, base_size);
-found_cache_entry:
if (!keep_cache) {
ent->data = NULL;
ent->lru.next->prev = ent->lru.prev;
* This is costly but should happen only in the presence
* of a corrupted pack, and is better than failing outright.
*/
- struct revindex_entry *revidx = find_pack_revindex(p, base_offset);
- const unsigned char *base_sha1 =
- nth_packed_object_sha1(p, revidx->nr);
+ struct revindex_entry *revidx;
+ const unsigned char *base_sha1;
+ revidx = find_pack_revindex(p, base_offset);
+ if (!revidx)
+ return NULL;
+ base_sha1 = nth_packed_object_sha1(p, revidx->nr);
error("failed to read delta base object %s"
" at offset %"PRIuMAX" from %s",
sha1_to_hex(base_sha1), (uintmax_t)base_offset,
return result;
}
+int do_check_packed_object_crc;
+
void *unpack_entry(struct packed_git *p, off_t obj_offset,
enum object_type *type, unsigned long *sizep)
{
off_t curpos = obj_offset;
void *data;
+ if (do_check_packed_object_crc && p->index_version > 1) {
+ struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
+ unsigned long len = revidx[1].offset - obj_offset;
+ if (check_pack_crc(p, &w_curs, obj_offset, len, revidx->nr)) {
+ const unsigned char *sha1 =
+ nth_packed_object_sha1(p, revidx->nr);
+ error("bad packed object CRC for %s",
+ sha1_to_hex(sha1));
+ mark_bad_packed_object(p, sha1);
+ unuse_pack(&w_curs);
+ return NULL;
+ }
+ }
+
*type = unpack_object_header(p, &w_curs, &curpos, sizep);
switch (*type) {
case OBJ_OFS_DELTA:
status = error("unable to parse %s header", sha1_to_hex(sha1));
else if (sizep)
*sizep = size;
- inflateEnd(&stream);
+ git_inflate_end(&stream);
munmap(map, mapsize);
return status;
}
if (!find_pack_entry(sha1, &e, NULL))
return status;
}
- return packed_object_info(e.p, e.offset, sizep);
+
+ status = packed_object_info(e.p, e.offset, sizep);
+ if (status < 0) {
+ mark_bad_packed_object(e.p, sha1);
+ status = sha1_object_info(sha1, sizep);
+ }
+
+ return status;
}
static void *read_packed_sha1(const unsigned char *sha1,
static int cached_object_nr, cached_object_alloc;
static struct cached_object empty_tree = {
- /* empty tree sha1: 4b825dc642cb6eb9a060e54bf8d69288fbee4904 */
- "\x4b\x82\x5d\xc6\x42\xcb\x6e\xb9\xa0\x60"
- "\xe5\x4b\xf8\xd6\x92\x88\xfb\xee\x49\x04",
+ EMPTY_TREE_SHA1_BIN,
OBJ_TREE,
"",
0
const char *type, unsigned char *sha1,
char *hdr, int *hdrlen)
{
- SHA_CTX c;
+ git_SHA_CTX c;
/* Generate the header */
*hdrlen = sprintf(hdr, "%s %lu", type, len)+1;
/* Sha1.. */
- SHA1_Init(&c);
- SHA1_Update(&c, hdr, *hdrlen);
- SHA1_Update(&c, buf, len);
- SHA1_Final(sha1, &c);
+ git_SHA1_Init(&c);
+ git_SHA1_Update(&c, hdr, *hdrlen);
+ git_SHA1_Update(&c, buf, len);
+ git_SHA1_Final(sha1, &c);
}
/*
fsync_or_die(fd, "sha1 file");
fchmod(fd, 0444);
if (close(fd) != 0)
- die("unable to write sha1 file");
+ die("error when closing sha1 file (%s)", strerror(errno));
}
/* Size of directory component, including the ending '/' */
return has_loose_object(sha1);
}
-int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object)
+static int index_mem(unsigned char *sha1, void *buf, size_t size,
+ int write_object, enum object_type type, const char *path)
{
- struct strbuf buf;
- int ret;
-
- strbuf_init(&buf, 0);
- if (strbuf_read(&buf, fd, 4096) < 0) {
- strbuf_release(&buf);
- return -1;
- }
-
- if (!type)
- type = blob_type;
- if (write_object)
- ret = write_sha1_file(buf.buf, buf.len, type, sha1);
- else
- ret = hash_sha1_file(buf.buf, buf.len, type, sha1);
- strbuf_release(&buf);
-
- return ret;
-}
-
-int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
- enum object_type type, const char *path)
-{
- size_t size = xsize_t(st->st_size);
- void *buf = NULL;
int ret, re_allocated = 0;
- if (size)
- buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
- close(fd);
-
if (!type)
type = OBJ_BLOB;
/*
* Convert blobs to git internal format
*/
- if ((type == OBJ_BLOB) && S_ISREG(st->st_mode)) {
- struct strbuf nbuf;
- strbuf_init(&nbuf, 0);
+ if ((type == OBJ_BLOB) && path) {
+ struct strbuf nbuf = STRBUF_INIT;
if (convert_to_git(path, buf, size, &nbuf,
write_object ? safe_crlf : 0)) {
- munmap(buf, size);
buf = strbuf_detach(&nbuf, &size);
re_allocated = 1;
}
ret = write_sha1_file(buf, size, typename(type), sha1);
else
ret = hash_sha1_file(buf, size, typename(type), sha1);
- if (re_allocated) {
+ if (re_allocated)
free(buf);
- return ret;
- }
- if (size)
+ return ret;
+}
+
+int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
+ enum object_type type, const char *path)
+{
+ int ret;
+ size_t size = xsize_t(st->st_size);
+
+ if (!S_ISREG(st->st_mode)) {
+ struct strbuf sbuf = STRBUF_INIT;
+ if (strbuf_read(&sbuf, fd, 4096) >= 0)
+ ret = index_mem(sha1, sbuf.buf, sbuf.len, write_object,
+ type, path);
+ else
+ ret = -1;
+ strbuf_release(&sbuf);
+ } else if (size) {
+ void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
+ ret = index_mem(sha1, buf, size, write_object, type, path);
munmap(buf, size);
+ } else
+ ret = index_mem(sha1, NULL, size, write_object, type, path);
+ close(fd);
return ret;
}
int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object)
{
int fd;
- char *target;
- size_t len;
+ struct strbuf sb = STRBUF_INIT;
switch (st->st_mode & S_IFMT) {
case S_IFREG:
path);
break;
case S_IFLNK:
- len = xsize_t(st->st_size);
- target = xmalloc(len + 1);
- if (readlink(path, target, len + 1) != st->st_size) {
+ if (strbuf_readlink(&sb, path, st->st_size)) {
char *errstr = strerror(errno);
- free(target);
return error("readlink(\"%s\"): %s", path,
errstr);
}
if (!write_object)
- hash_sha1_file(target, len, blob_type, sha1);
- else if (write_sha1_file(target, len, blob_type, sha1))
+ hash_sha1_file(sb.buf, sb.len, blob_type, sha1);
+ else if (write_sha1_file(sb.buf, sb.len, blob_type, sha1))
return error("%s: failed to insert into database",
path);
- free(target);
+ strbuf_release(&sb);
break;
case S_IFDIR:
return resolve_gitlink_ref(path, "HEAD", sha1);