Re: [PATCH v2] receive-pack: not receive pack file with large object

From: Han Xin <chiyutianyi@gmail.com>
Date: Nov 11, 2021, 03:03 UTC
Message-ID: <20211111030302.75694-1-hanxin.hx@alibaba-inc.com>
In-Reply-To: <patch-v10-17.17-838df0a979b-20211001T091051Z-avarab@gmail.com>

Ævar Arnfjörð Bjarmason <avarab@gmail.com> writes: ...

Show 55 quoted lines

> diff --git a/object-file.c b/object-file.c
> index fe95285f405..49561e31551 100644
> --- a/object-file.c
> +++ b/object-file.c
> @@ -1084,9 +1084,11 @@ void *xmmap(void *start, size_t length,
> * the streaming interface and rehash it to do the same.
> */
> int check_object_signature(struct repository *r, const struct object_id *oid,
> - void *map, unsigned long size, const char *type)
> + void *map, unsigned long size, const char *type,
> + struct object_id *real_oidp)
> {
> - struct object_id real_oid;
> + struct object_id tmp;
> + struct object_id *real_oid = real_oidp ? real_oidp : &tmp;
> enum object_type obj_type;
> struct git_istream *st;
> git_hash_ctx c;
> @@ -1094,8 +1096,8 @@ int check_object_signature(struct repository *r, const struct object_id *oid,
> int hdrlen;
>
> if (map) {
> - hash_object_file(r->hash_algo, map, size, type, &real_oid);
> - return !oideq(oid, &real_oid) ? -1 : 0;
> + hash_object_file(r->hash_algo, map, size, type, real_oid);
> + return !oideq(oid, real_oid) ? -1 : 0;
> }
>
> st = open_istream(r, oid, &obj_type, &size, NULL);
> @@ -1120,9 +1122,9 @@ int check_object_signature(struct repository *r, const struct object_id *oid,
> break;
> r->hash_algo->update_fn(&c, buf, readlen);
> }
> - r->hash_algo->final_oid_fn(&real_oid, &c);
> + r->hash_algo->final_oid_fn(real_oid, &c);
> close_istream(st);
> - return !oideq(oid, &real_oid) ? -1 : 0;
> + return !oideq(oid, real_oid) ? -1 : 0;
> }
>
> int git_open_cloexec(const char *name, int flags)
> @@ -2572,6 +2574,7 @@ static int check_stream_oid(git_zstream *stream,
>
> int read_loose_object(const char *path,
> const struct object_id *expected_oid,
> + struct object_id *real_oid,
> void **contents,
> struct object_info *oi)
> {
> @@ -2582,8 +2585,6 @@ int read_loose_object(const char *path,
> char hdr[MAX_HEADER_LEN];
> unsigned long *size = oi->sizep;
>
> - *contents = NULL;
> -

Deleting "*contents = NULL;" here will cause a memory free error. When reading a large loose blob ( large than big_file_threshold), it will enter the following block and *content will not be set:

	if (*oi->typep == OBJ_BLOB && *size > big_file_threshold) {
		if (check_stream_oid(&stream, hdr, *size, path, expected_oid) < 0)
			goto out;
	} else {
		...
	}

This test case can illustrate this problem:

test_expect_success 'fsck large loose blob' '
	blob=$(echo large | git hash-object -w --stdin) &&
	git -c core.bigfilethreshold=4 fsck
'

git(73697,0x1198f1e00) malloc: *** error for object 0x36: pointer being freed was not allocated git(73697,0x1198f1e00) malloc: *** set a breakpoint in malloc_error_break to debug ./test-lib.sh: line 947: 73697 Abort trap: 6 git -c core.bigfilethreshold=4 fsck

Show 14 quoted lines

> map = map_loose_object_1(the_repository, path, NULL, &mapsize);
> if (!map) {
> error_errno(_("unable to mmap %s"), path);
> @@ -2613,9 +2614,7 @@ int read_loose_object(const char *path,
> goto out;
> }
> if (check_object_signature(the_repository, expected_oid,
> - *contents, *size, oi->type_name->buf)) {
> - error(_("hash mismatch for %s (expected %s)"), path,
> - oid_to_hex(expected_oid));
> + *contents, *size, oi->type_name->buf, real_oid)) {
> free(*contents);
> goto out;
> }

...