static int keep_unreachable, unpack_unreachable, include_tag;
static int local;
static int incremental;
+static int ignore_packed_keep;
static int allow_ofs_delta;
static const char *base_name;
static int progress = 1;
type = entry->type;
/* write limit if limited packsize and not first object */
- limit = pack_size_limit && nr_written ?
- pack_size_limit - write_offset : 0;
+ if (!pack_size_limit || !nr_written)
+ limit = 0;
+ else if (pack_size_limit <= write_offset)
+ /*
+ * the earlier object did not fit the limit; avoid
+ * mistaking this with unlimited (i.e. limit = 0).
+ */
+ limit = 1;
+ else
+ limit = pack_size_limit - write_offset;
if (!entry->delta)
usable_delta = 0; /* no delta */
*/
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++;
return 0;
}
+ if (!exclude && local && has_loose_object_nonlocal(sha1))
+ return 0;
+
for (p = packed_git; p; p = p->next) {
off_t offset = find_pack_entry_one(sha1, p);
if (offset) {
return 0;
if (local && !p->pack_local)
return 0;
+ if (ignore_packed_keep && p->pack_local && p->pack_keep)
+ return 0;
}
}
* 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);
}
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;
incremental = 1;
continue;
}
+ if (!strcmp("--honor-pack-keep", arg)) {
+ ignore_packed_keep = 1;
+ continue;
+ }
if (!prefixcmp(arg, "--compression=")) {
char *end;
int level = strtoul(arg+14, &end, 0);
#define read_cache() read_index(&the_index)
#define read_cache_from(path) read_index_from(&the_index, (path))
+#define is_cache_unborn() is_index_unborn(&the_index)
#define read_cache_unmerged() read_index_unmerged(&the_index)
#define write_cache(newfd, cache, entries) write_index(&the_index, (newfd))
#define discard_cache() discard_index(&the_index)
/* Initialize and use the cache information */
extern int read_index(struct index_state *);
extern int read_index_from(struct index_state *, const char *path);
+extern int is_index_unborn(struct index_state *);
extern int read_index_unmerged(struct index_state *);
extern int write_index(const struct index_state *, int newfd);
extern int discard_index(struct index_state *);
extern void set_alternate_index_output(const char *);
extern int close_lock_file(struct lock_file *);
extern void rollback_lock_file(struct lock_file *);
-extern int delete_ref(const char *, const unsigned char *sha1);
+extern int delete_ref(const char *, const unsigned char *sha1, int delopt);
/* Environment bits from configuration mechanism */
extern int trust_executable_bit;
#define DATA_CHANGED 0x0020
#define TYPE_CHANGED 0x0040
+extern char *mksnpath(char *buf, size_t n, const char *fmt, ...)
+ __attribute__((format (printf, 3, 4)));
+extern char *git_snpath(char *buf, size_t n, const char *fmt, ...)
+ __attribute__((format (printf, 3, 4)));
+extern char *git_pathdup(const char *fmt, ...)
+ __attribute__((format (printf, 1, 2)));
+
/* Return a statically allocated filename matching the sha1 signature */
extern char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
extern char *git_path(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
/* just like read_sha1_file(), but non fatal in presence of bad objects */
extern void *read_object(const unsigned char *sha1, enum object_type *type, unsigned long *size);
+ /* global flag to enable extra checks when accessing packed objects */
+ extern int do_check_packed_object_crc;
+
extern int check_sha1_signature(const unsigned char *sha1, void *buf, unsigned long size, const char *type);
extern int move_temp_to_file(const char *tmpfile, const char *filename);
extern int has_sha1_pack(const unsigned char *sha1, const char **ignore);
extern int has_sha1_file(const unsigned char *sha1);
+extern int has_loose_object_nonlocal(const unsigned char *sha1);
extern int has_pack_file(const unsigned char *sha1);
extern int has_pack_index(const unsigned char *sha1);
int index_version;
time_t mtime;
int pack_fd;
- int pack_local;
+ unsigned pack_local:1,
+ pack_keep:1;
unsigned char sha1[20];
/* something like ".git/objects/pack/xxxxx.pack" */
char pack_name[FLEX_ARRAY]; /* more */
extern off_t nth_packed_object_offset(const struct packed_git *, uint32_t);
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_gently(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep);
+ 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 const char *packed_object_info_detail(struct packed_git *, off_t, unsigned long *, unsigned long *, unsigned int *, unsigned char *);
extern int matches_pack_name(struct packed_git *p, const char *name);
die("pack has bad object at offset %lu: %s", offset, buf);
}
+static void free_base_data(struct base_data *c)
+{
+ if (c->data) {
+ free(c->data);
+ c->data = NULL;
+ base_cache_used -= c->size;
+ }
+}
+
static void prune_base_data(struct base_data *retain)
{
struct base_data *b = base_cache;
for (b = base_cache;
base_cache_used > delta_base_cache_limit && b;
b = b->child) {
- if (b->data && b != retain) {
- free(b->data);
- b->data = NULL;
- base_cache_used -= b->size;
- }
+ if (b->data && b != retain)
+ free_base_data(b);
}
}
c->base = base;
c->child = NULL;
- base_cache_used += c->size;
+ if (c->data)
+ base_cache_used += c->size;
prune_base_data(c);
}
base->child = NULL;
else
base_cache = NULL;
- if (c->data) {
- free(c->data);
- base_cache_used -= c->size;
- }
+ free_base_data(c);
}
static void *unpack_entry_data(unsigned long offset, unsigned long size)
base_offset = (base_offset << 7) + (c & 127);
}
delta_base->offset = obj->idx.offset - base_offset;
- if (delta_base->offset >= obj->idx.offset)
+ if (delta_base->offset <= 0 || delta_base->offset >= obj->idx.offset)
bad_object(obj->idx.offset, "delta base offset is out of bound");
break;
case OBJ_COMMIT:
return -first-1;
}
-static int find_delta_children(const union delta_base *base,
- int *first_index, int *last_index)
+static void find_delta_children(const union delta_base *base,
+ int *first_index, int *last_index)
{
int first = find_delta(base);
int last = first;
int end = nr_deltas - 1;
- if (first < 0)
- return -1;
+ if (first < 0) {
+ *first_index = 0;
+ *last_index = -1;
+ return;
+ }
while (first > 0 && !memcmp(&deltas[first - 1].base, base, UNION_BASE_SZ))
--first;
while (last < end && !memcmp(&deltas[last + 1].base, base, UNION_BASE_SZ))
++last;
*first_index = first;
*last_index = last;
- return 0;
}
static void sha1_object(const void *data, unsigned long size,
free(raw);
if (!c->data)
bad_object(obj->idx.offset, "failed to apply delta");
- } else
+ } else {
c->data = get_data_from_pack(obj);
+ c->size = obj->size;
+ }
base_cache_used += c->size;
prune_base_data(c);
}
static void resolve_delta(struct object_entry *delta_obj,
- struct base_data *base_obj, enum object_type type)
+ struct base_data *base, struct base_data *result)
{
- void *delta_data;
- unsigned long delta_size;
- union delta_base delta_base;
- int j, first, last;
- struct base_data result;
+ void *base_data, *delta_data;
- delta_obj->real_type = type;
+ delta_obj->real_type = base->obj->real_type;
delta_data = get_data_from_pack(delta_obj);
- delta_size = delta_obj->size;
- result.data = patch_delta(get_base_data(base_obj), base_obj->size,
- delta_data, delta_size,
- &result.size);
+ base_data = get_base_data(base);
+ result->obj = delta_obj;
+ result->data = patch_delta(base_data, base->size,
+ delta_data, delta_obj->size, &result->size);
free(delta_data);
- if (!result.data)
+ if (!result->data)
bad_object(delta_obj->idx.offset, "failed to apply delta");
- sha1_object(result.data, result.size, type, delta_obj->idx.sha1);
+ sha1_object(result->data, result->size, delta_obj->real_type,
+ delta_obj->idx.sha1);
nr_resolved_deltas++;
+}
+
+static void find_unresolved_deltas(struct base_data *base,
+ struct base_data *prev_base)
+{
+ int i, ref_first, ref_last, ofs_first, ofs_last;
+
+ /*
+ * This is a recursive function. Those brackets should help reducing
+ * stack usage by limiting the scope of the delta_base union.
+ */
+ {
+ union delta_base base_spec;
+
+ hashcpy(base_spec.sha1, base->obj->idx.sha1);
+ find_delta_children(&base_spec, &ref_first, &ref_last);
- result.obj = delta_obj;
- link_base_data(base_obj, &result);
+ memset(&base_spec, 0, sizeof(base_spec));
+ base_spec.offset = base->obj->idx.offset;
+ find_delta_children(&base_spec, &ofs_first, &ofs_last);
+ }
- hashcpy(delta_base.sha1, delta_obj->idx.sha1);
- if (!find_delta_children(&delta_base, &first, &last)) {
- for (j = first; j <= last; j++) {
- struct object_entry *child = objects + deltas[j].obj_no;
- if (child->real_type == OBJ_REF_DELTA)
- resolve_delta(child, &result, type);
+ if (ref_last == -1 && ofs_last == -1) {
+ free(base->data);
+ return;
+ }
+
+ link_base_data(prev_base, 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);
}
}
- memset(&delta_base, 0, sizeof(delta_base));
- delta_base.offset = delta_obj->idx.offset;
- if (!find_delta_children(&delta_base, &first, &last)) {
- for (j = first; j <= last; j++) {
- struct object_entry *child = objects + deltas[j].obj_no;
- if (child->real_type == OBJ_OFS_DELTA)
- resolve_delta(child, &result, type);
+ 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);
}
}
- unlink_base_data(&result);
+ unlink_base_data(base);
}
static int compare_delta_entry(const void *a, const void *b)
progress = start_progress("Resolving deltas", nr_deltas);
for (i = 0; i < nr_objects; i++) {
struct object_entry *obj = &objects[i];
- union delta_base base;
- int j, ref, ref_first, ref_last, ofs, ofs_first, ofs_last;
struct base_data base_obj;
if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA)
continue;
- hashcpy(base.sha1, obj->idx.sha1);
- ref = !find_delta_children(&base, &ref_first, &ref_last);
- memset(&base, 0, sizeof(base));
- base.offset = obj->idx.offset;
- ofs = !find_delta_children(&base, &ofs_first, &ofs_last);
- if (!ref && !ofs)
- continue;
- base_obj.data = get_data_from_pack(obj);
- base_obj.size = obj->size;
base_obj.obj = obj;
- link_base_data(NULL, &base_obj);
-
- if (ref)
- for (j = ref_first; j <= ref_last; j++) {
- struct object_entry *child = objects + deltas[j].obj_no;
- if (child->real_type == OBJ_REF_DELTA)
- resolve_delta(child, &base_obj, obj->type);
- }
- if (ofs)
- for (j = ofs_first; j <= ofs_last; j++) {
- struct object_entry *child = objects + deltas[j].obj_no;
- if (child->real_type == OBJ_OFS_DELTA)
- resolve_delta(child, &base_obj, obj->type);
- }
- unlink_base_data(&base_obj);
+ base_obj.data = NULL;
+ find_unresolved_deltas(&base_obj, NULL);
display_progress(progress, nr_resolved_deltas);
}
}
for (i = 0; i < n; i++) {
struct delta_entry *d = sorted_by_pos[i];
enum object_type type;
- int j, first, last;
struct base_data base_obj;
if (objects[d->obj_no].real_type != OBJ_REF_DELTA)
die("local object %s is corrupt", sha1_to_hex(d->base.sha1));
base_obj.obj = append_obj_to_pack(f, d->base.sha1,
base_obj.data, base_obj.size, type);
- link_base_data(NULL, &base_obj);
-
- find_delta_children(&d->base, &first, &last);
- for (j = first; j <= last; j++) {
- struct object_entry *child = objects + deltas[j].obj_no;
- if (child->real_type == OBJ_REF_DELTA)
- resolve_delta(child, &base_obj, type);
- }
-
- unlink_base_data(&base_obj);
+ find_unresolved_deltas(&base_obj, NULL);
display_progress(progress, nr_resolved_deltas);
}
free(sorted_by_pos);
read_info_alternates(get_object_directory(), 0);
}
-static int has_loose_object(const unsigned char *sha1)
+static int has_loose_object_local(const unsigned char *sha1)
{
char *name = sha1_file_name(sha1);
- struct alternate_object_database *alt;
+ return !access(name, F_OK);
+}
- if (!access(name, F_OK))
- return 1;
+int has_loose_object_nonlocal(const unsigned char *sha1)
+{
+ struct alternate_object_database *alt;
prepare_alt_odb();
for (alt = alt_odb_list; alt; alt = alt->next) {
- name = alt->name;
- fill_sha1_path(name, sha1);
+ fill_sha1_path(alt->name, sha1);
if (!access(alt->base, F_OK))
return 1;
}
return 0;
}
+static int has_loose_object(const unsigned char *sha1)
+{
+ return has_loose_object_local(sha1) ||
+ has_loose_object_nonlocal(sha1);
+}
+
static unsigned int pack_used_ctr;
static unsigned int pack_mmap_calls;
static unsigned int peak_pack_open_windows;
return NULL;
}
memcpy(p->pack_name, path, path_len);
+
+ strcpy(p->pack_name + path_len, ".keep");
+ if (!access(p->pack_name, F_OK))
+ p->pack_keep = 1;
+
strcpy(p->pack_name + path_len, ".pack");
if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) {
free(p);
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;
* 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;
} 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");
+ 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;
* 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);
+ return NULL;
+ }
+ }
+
*type = unpack_object_header(p, &w_curs, &curpos, sizep);
switch (*type) {
case OBJ_OFS_DELTA:
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,
'rm -rf .git
git init &&
i=1 &&
- while test $i -le 100
+ while test $i -le 100
do
- i=`printf '%03i' $i`
- echo $i >file_$i &&
- test-genrandom "$i" 8192 >>file_$i &&
- git update-index --add file_$i &&
- i=`expr $i + 1` || return 1
+ iii=`printf '%03i' $i`
+ test-genrandom "bar" 200 > wide_delta_$iii &&
+ test-genrandom "baz $iii" 50 >> wide_delta_$iii &&
+ test-genrandom "foo"$i 100 > deep_delta_$iii &&
+ test-genrandom "foo"`expr $i + 1` 100 >> deep_delta_$iii &&
+ test-genrandom "foo"`expr $i + 2` 100 >> deep_delta_$iii &&
+ echo $iii >file_$iii &&
+ test-genrandom "$iii" 8192 >>file_$iii &&
+ git update-index --add file_$iii deep_delta_$iii wide_delta_$iii &&
+ i=`expr $i + 1` || return 1
done &&
{ echo 101 && test-genrandom 100 8192; } >file_101 &&
git update-index --add file_101 &&
'64-bit offsets: index-pack result should match pack-objects one' \
'cmp "test-3-${pack3}.idx" "3.idx"'
+# returns the object number for given object in given pack index
+index_obj_nr()
+{
+ idx_file=$1
+ object_sha1=$2
+ nr=0
+ git show-index < $idx_file |
+ while read offs sha1 extra
+ do
+ nr=$(($nr + 1))
+ test "$sha1" = "$object_sha1" || continue
+ echo "$(($nr - 1))"
+ break
+ done
+}
+
+# returns the pack offset for given object as found in given pack index
+index_obj_offset()
+{
+ idx_file=$1
+ object_sha1=$2
+ git show-index < $idx_file | grep $object_sha1 |
+ ( read offs extra && echo "$offs" )
+}
+
test_expect_success \
'[index v1] 1) stream pack to repository' \
'git index-pack --index-version=1 --stdin < "test-1-${pack1}.pack" &&
test_expect_success \
'[index v1] 2) create a stealth corruption in a delta base reference' \
- '# this test assumes a delta smaller than 16 bytes at the end of the pack
- git show-index <1.idx | sort -n | sed -ne \$p | (
- read delta_offs delta_sha1 &&
- git cat-file blob "$delta_sha1" > blob_1 &&
- chmod +w ".git/objects/pack/pack-${pack1}.pack" &&
- dd of=".git/objects/pack/pack-${pack1}.pack" seek=$(($delta_offs + 1)) \
- if=".git/objects/pack/pack-${pack1}.idx" skip=$((256 * 4 + 4)) \
- bs=1 count=20 conv=notrunc &&
- git cat-file blob "$delta_sha1" > blob_2 )'
+ '# This test assumes file_101 is a delta smaller than 16 bytes.
+ # It should be against file_100 but we substitute its base for file_099
+ sha1_101=`git hash-object file_101` &&
+ sha1_099=`git hash-object file_099` &&
+ offs_101=`index_obj_offset 1.idx $sha1_101` &&
+ nr_099=`index_obj_nr 1.idx $sha1_099` &&
+ chmod +w ".git/objects/pack/pack-${pack1}.pack" &&
+ dd of=".git/objects/pack/pack-${pack1}.pack" seek=$(($offs_101 + 1)) \
+ if=".git/objects/pack/pack-${pack1}.idx" \
+ skip=$((4 + 256 * 4 + $nr_099 * 24)) \
+ bs=1 count=20 conv=notrunc &&
+ git cat-file blob $sha1_101 > file_101_foo1'
test_expect_success \
'[index v1] 3) corrupted delta happily returned wrong data' \
- '! cmp blob_1 blob_2'
+ 'test -f file_101_foo1 && ! cmp file_101 file_101_foo1'
test_expect_success \
'[index v1] 4) confirm that the pack is actually corrupted' \
test_expect_success \
'[index v2] 2) create a stealth corruption in a delta base reference' \
- '# this test assumes a delta smaller than 16 bytes at the end of the pack
- git show-index <1.idx | sort -n | sed -ne \$p | (
- read delta_offs delta_sha1 delta_crc &&
- git cat-file blob "$delta_sha1" > blob_3 &&
- chmod +w ".git/objects/pack/pack-${pack1}.pack" &&
- dd of=".git/objects/pack/pack-${pack1}.pack" seek=$(($delta_offs + 1)) \
- if=".git/objects/pack/pack-${pack1}.idx" skip=$((8 + 256 * 4)) \
- bs=1 count=20 conv=notrunc &&
- git cat-file blob "$delta_sha1" > blob_4 )'
+ '# This test assumes file_101 is a delta smaller than 16 bytes.
+ # It should be against file_100 but we substitute its base for file_099
+ sha1_101=`git hash-object file_101` &&
+ sha1_099=`git hash-object file_099` &&
+ offs_101=`index_obj_offset 1.idx $sha1_101` &&
+ nr_099=`index_obj_nr 1.idx $sha1_099` &&
+ chmod +w ".git/objects/pack/pack-${pack1}.pack" &&
+ dd of=".git/objects/pack/pack-${pack1}.pack" seek=$(($offs_101 + 1)) \
+ if=".git/objects/pack/pack-${pack1}.idx" \
+ skip=$((8 + 256 * 4 + $nr_099 * 20)) \
+ bs=1 count=20 conv=notrunc &&
+ git cat-file blob $sha1_101 > file_101_foo2'
test_expect_success \
'[index v2] 3) corrupted delta happily returned wrong data' \
- '! cmp blob_3 blob_4'
+ 'test -f file_101_foo2 && ! cmp file_101 file_101_foo2'
test_expect_success \
'[index v2] 4) confirm that the pack is actually corrupted' \
test_expect_success \
'[index v2] 5) pack-objects refuses to reuse corrupted data' \
- 'test_must_fail git pack-objects test-5 <obj-list'
+ 'test_must_fail git pack-objects test-5 <obj-list &&
+ test_must_fail git pack-objects --no-reuse-object test-6 <obj-list'
test_expect_success \
'[index v2] 6) verify-pack detects CRC mismatch' \
'rm -f .git/objects/pack/* &&
git index-pack --index-version=2 --stdin < "test-1-${pack1}.pack" &&
git verify-pack ".git/objects/pack/pack-${pack1}.pack" &&
+ obj=`git hash-object file_001` &&
+ nr=`index_obj_nr ".git/objects/pack/pack-${pack1}.idx" $obj` &&
chmod +w ".git/objects/pack/pack-${pack1}.idx" &&
dd if=/dev/zero of=".git/objects/pack/pack-${pack1}.idx" conv=notrunc \
- bs=1 count=4 seek=$((8 + 256 * 4 + `wc -l <obj-list` * 20 + 0)) &&
+ bs=1 count=4 seek=$((8 + 256 * 4 + `wc -l <obj-list` * 20 + $nr * 4)) &&
( while read obj
do git cat-file -p $obj >/dev/null || exit 1
done <obj-list ) &&