1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-04 17:06:12 +02:00
git/object.c
Jeff King 8db2dad7a0 parse_object(): check on-disk type of suspected blob
In parse_object(), we try to handle blobs by streaming rather than
loading them entirely into memory. The most common case here will be
that we haven't seen the object yet and check oid_object_info(), which
tells us we have a blob.

But we trigger this code on one other case: when we have an in-memory
object struct with type OBJ_BLOB (and without its "parsed" flag set,
since otherwise we'd return early from the function). This indicates
that some other part of the code suspected we have a blob (e.g., it was
mentioned by a tree or tag) but we haven't yet looked at the on-disk
copy.

In this case before hitting the streaming path, we check if we have the
object on-disk at all. This is mostly pointless extra work, as the
streaming path would complain if it couldn't open the object (albeit
with the message "hash mismatch", which is a little misleading).

But it's also insufficient to catch all problems. The streaming code
will only tell us "yes, the on-disk object matches the oid". But it
doesn't actually confirm that what we found was indeed a blob, and
neither does repo_has_object_file().

One way to improve this would be to teach stream_object_signature() to
check the type (either by returning it to us to check, or taking an
"expected" type). But there's an even simpler fix here: if we suspect
the object is a blob, just call oid_object_info() to confirm that we
have it on-disk, and that it really is a blob.

This is slightly less efficient than teaching stream_object_signature()
to do it (since it has to open the object already). But this case very
rarely comes up. In practice, we usually don't have any clue what the
type is, in which case we already call oid_object_info(). This
"suspected" case happens only when some other code created an object
struct but didn't actually parse the blob, which is actually tricky to
trigger at all (see the discussion of the test below).

I reworked the conditional a bit so that instead of:

  if ((suspected_blob && oid_object_info() == OBJ_BLOB)
      (no_clue && oid_object_info() == OBJ_BLOB)

we have the simpler:

  if ((suspected_blob || no_clue) && oid_object_info() == OBJ_BLOB)

This is shorter, but also reflects what we really want say, which is
"have we ruled out this being a blob; if not, check it on-disk".

In either case, if oid_object_info() fails to tell us it's a blob, we'll
skip the streaming code path and call repo_read_object_file(), just as
before. And if we really do have a mismatch with the existing object
struct, we'll eventually call lookup_commit(), etc, via
parse_object_buffer(), which will complain that it doesn't match our
existing obj->type.

So this fixes one of the lingering expect_failure cases from 0616617c7e
(t: introduce tests for unexpected object types, 2019-04-09).  That test
works by peeling a tag that claims to point to a blob (triggering us to
create the struct), but really points to something else, which we later
discover when we call parse_object() as part of the actual traversal).
Prior to this commit, we'd quietly check the sha1 and mark the blob as
"parsed". Now we correctly complain about the mismatch.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Taylor Blau <me@ttaylorr.com>
2022-11-18 13:59:31 -05:00

617 lines
14 KiB
C

#include "cache.h"
#include "object.h"
#include "replace-object.h"
#include "object-store.h"
#include "blob.h"
#include "tree.h"
#include "commit.h"
#include "tag.h"
#include "alloc.h"
#include "packfile.h"
#include "commit-graph.h"
unsigned int get_max_object_index(void)
{
return the_repository->parsed_objects->obj_hash_size;
}
struct object *get_indexed_object(unsigned int idx)
{
return the_repository->parsed_objects->obj_hash[idx];
}
static const char *object_type_strings[] = {
NULL, /* OBJ_NONE = 0 */
"commit", /* OBJ_COMMIT = 1 */
"tree", /* OBJ_TREE = 2 */
"blob", /* OBJ_BLOB = 3 */
"tag", /* OBJ_TAG = 4 */
};
const char *type_name(unsigned int type)
{
if (type >= ARRAY_SIZE(object_type_strings))
return NULL;
return object_type_strings[type];
}
int type_from_string_gently(const char *str, ssize_t len, int gentle)
{
int i;
if (len < 0)
len = strlen(str);
for (i = 1; i < ARRAY_SIZE(object_type_strings); i++)
if (!strncmp(str, object_type_strings[i], len) &&
object_type_strings[i][len] == '\0')
return i;
if (gentle)
return -1;
die(_("invalid object type \"%s\""), str);
}
/*
* Return a numerical hash value between 0 and n-1 for the object with
* the specified sha1. n must be a power of 2. Please note that the
* return value is *not* consistent across computer architectures.
*/
static unsigned int hash_obj(const struct object_id *oid, unsigned int n)
{
return oidhash(oid) & (n - 1);
}
/*
* Insert obj into the hash table hash, which has length size (which
* must be a power of 2). On collisions, simply overflow to the next
* empty bucket.
*/
static void insert_obj_hash(struct object *obj, struct object **hash, unsigned int size)
{
unsigned int j = hash_obj(&obj->oid, size);
while (hash[j]) {
j++;
if (j >= size)
j = 0;
}
hash[j] = obj;
}
/*
* Look up the record for the given sha1 in the hash map stored in
* obj_hash. Return NULL if it was not found.
*/
struct object *lookup_object(struct repository *r, const struct object_id *oid)
{
unsigned int i, first;
struct object *obj;
if (!r->parsed_objects->obj_hash)
return NULL;
first = i = hash_obj(oid, r->parsed_objects->obj_hash_size);
while ((obj = r->parsed_objects->obj_hash[i]) != NULL) {
if (oideq(oid, &obj->oid))
break;
i++;
if (i == r->parsed_objects->obj_hash_size)
i = 0;
}
if (obj && i != first) {
/*
* Move object to where we started to look for it so
* that we do not need to walk the hash table the next
* time we look for it.
*/
SWAP(r->parsed_objects->obj_hash[i],
r->parsed_objects->obj_hash[first]);
}
return obj;
}
/*
* Increase the size of the hash map stored in obj_hash to the next
* power of 2 (but at least 32). Copy the existing values to the new
* hash map.
*/
static void grow_object_hash(struct repository *r)
{
int i;
/*
* Note that this size must always be power-of-2 to match hash_obj
* above.
*/
int new_hash_size = r->parsed_objects->obj_hash_size < 32 ? 32 : 2 * r->parsed_objects->obj_hash_size;
struct object **new_hash;
CALLOC_ARRAY(new_hash, new_hash_size);
for (i = 0; i < r->parsed_objects->obj_hash_size; i++) {
struct object *obj = r->parsed_objects->obj_hash[i];
if (!obj)
continue;
insert_obj_hash(obj, new_hash, new_hash_size);
}
free(r->parsed_objects->obj_hash);
r->parsed_objects->obj_hash = new_hash;
r->parsed_objects->obj_hash_size = new_hash_size;
}
void *create_object(struct repository *r, const struct object_id *oid, void *o)
{
struct object *obj = o;
obj->parsed = 0;
obj->flags = 0;
oidcpy(&obj->oid, oid);
if (r->parsed_objects->obj_hash_size - 1 <= r->parsed_objects->nr_objs * 2)
grow_object_hash(r);
insert_obj_hash(obj, r->parsed_objects->obj_hash,
r->parsed_objects->obj_hash_size);
r->parsed_objects->nr_objs++;
return obj;
}
void *object_as_type(struct object *obj, enum object_type type, int quiet)
{
if (obj->type == type)
return obj;
else if (obj->type == OBJ_NONE) {
if (type == OBJ_COMMIT)
init_commit_node((struct commit *) obj);
else
obj->type = type;
return obj;
}
else {
if (!quiet)
error(_("object %s is a %s, not a %s"),
oid_to_hex(&obj->oid),
type_name(obj->type), type_name(type));
return NULL;
}
}
struct object *lookup_unknown_object(struct repository *r, const struct object_id *oid)
{
struct object *obj = lookup_object(r, oid);
if (!obj)
obj = create_object(r, oid, alloc_object_node(r));
return obj;
}
struct object *lookup_object_by_type(struct repository *r,
const struct object_id *oid,
enum object_type type)
{
switch (type) {
case OBJ_COMMIT:
return (struct object *)lookup_commit(r, oid);
case OBJ_TREE:
return (struct object *)lookup_tree(r, oid);
case OBJ_TAG:
return (struct object *)lookup_tag(r, oid);
case OBJ_BLOB:
return (struct object *)lookup_blob(r, oid);
default:
BUG("unknown object type %d", type);
}
}
struct object *parse_object_buffer(struct repository *r, const struct object_id *oid, enum object_type type, unsigned long size, void *buffer, int *eaten_p)
{
struct object *obj;
*eaten_p = 0;
obj = NULL;
if (type == OBJ_BLOB) {
struct blob *blob = lookup_blob(r, oid);
if (blob) {
if (parse_blob_buffer(blob, buffer, size))
return NULL;
obj = &blob->object;
}
} else if (type == OBJ_TREE) {
struct tree *tree = lookup_tree(r, oid);
if (tree) {
obj = &tree->object;
if (!tree->buffer)
tree->object.parsed = 0;
if (!tree->object.parsed) {
if (parse_tree_buffer(tree, buffer, size))
return NULL;
*eaten_p = 1;
}
}
} else if (type == OBJ_COMMIT) {
struct commit *commit = lookup_commit(r, oid);
if (commit) {
if (parse_commit_buffer(r, commit, buffer, size, 1))
return NULL;
if (save_commit_buffer &&
!get_cached_commit_buffer(r, commit, NULL)) {
set_commit_buffer(r, commit, buffer, size);
*eaten_p = 1;
}
obj = &commit->object;
}
} else if (type == OBJ_TAG) {
struct tag *tag = lookup_tag(r, oid);
if (tag) {
if (parse_tag_buffer(r, tag, buffer, size))
return NULL;
obj = &tag->object;
}
} else {
warning(_("object %s has unknown type id %d"), oid_to_hex(oid), type);
obj = NULL;
}
return obj;
}
struct object *parse_object_or_die(const struct object_id *oid,
const char *name)
{
struct object *o = parse_object(the_repository, oid);
if (o)
return o;
die(_("unable to parse object: %s"), name ? name : oid_to_hex(oid));
}
struct object *parse_object_with_flags(struct repository *r,
const struct object_id *oid,
enum parse_object_flags flags)
{
int skip_hash = !!(flags & PARSE_OBJECT_SKIP_HASH_CHECK);
unsigned long size;
enum object_type type;
int eaten;
const struct object_id *repl = lookup_replace_object(r, oid);
void *buffer;
struct object *obj;
obj = lookup_object(r, oid);
if (obj && obj->parsed)
return obj;
if (skip_hash) {
struct commit *commit = lookup_commit_in_graph(r, repl);
if (commit)
return &commit->object;
}
if ((!obj || (obj && obj->type == OBJ_BLOB)) &&
oid_object_info(r, oid, NULL) == OBJ_BLOB) {
if (!skip_hash && stream_object_signature(r, repl) < 0) {
error(_("hash mismatch %s"), oid_to_hex(oid));
return NULL;
}
parse_blob_buffer(lookup_blob(r, oid), NULL, 0);
return lookup_object(r, oid);
}
buffer = repo_read_object_file(r, oid, &type, &size);
if (buffer) {
if (!skip_hash &&
check_object_signature(r, repl, buffer, size, type) < 0) {
free(buffer);
error(_("hash mismatch %s"), oid_to_hex(repl));
return NULL;
}
obj = parse_object_buffer(r, oid, type, size,
buffer, &eaten);
if (!eaten)
free(buffer);
return obj;
}
return NULL;
}
struct object *parse_object(struct repository *r, const struct object_id *oid)
{
return parse_object_with_flags(r, oid, 0);
}
struct object_list *object_list_insert(struct object *item,
struct object_list **list_p)
{
struct object_list *new_list = xmalloc(sizeof(struct object_list));
new_list->item = item;
new_list->next = *list_p;
*list_p = new_list;
return new_list;
}
int object_list_contains(struct object_list *list, struct object *obj)
{
while (list) {
if (list->item == obj)
return 1;
list = list->next;
}
return 0;
}
void object_list_free(struct object_list **list)
{
while (*list) {
struct object_list *p = *list;
*list = p->next;
free(p);
}
}
/*
* A zero-length string to which object_array_entry::name can be
* initialized without requiring a malloc/free.
*/
static char object_array_slopbuf[1];
void add_object_array_with_path(struct object *obj, const char *name,
struct object_array *array,
unsigned mode, const char *path)
{
unsigned nr = array->nr;
unsigned alloc = array->alloc;
struct object_array_entry *objects = array->objects;
struct object_array_entry *entry;
if (nr >= alloc) {
alloc = (alloc + 32) * 2;
REALLOC_ARRAY(objects, alloc);
array->alloc = alloc;
array->objects = objects;
}
entry = &objects[nr];
entry->item = obj;
if (!name)
entry->name = NULL;
else if (!*name)
/* Use our own empty string instead of allocating one: */
entry->name = object_array_slopbuf;
else
entry->name = xstrdup(name);
entry->mode = mode;
if (path)
entry->path = xstrdup(path);
else
entry->path = NULL;
array->nr = ++nr;
}
void add_object_array(struct object *obj, const char *name, struct object_array *array)
{
add_object_array_with_path(obj, name, array, S_IFINVALID, NULL);
}
/*
* Free all memory associated with an entry; the result is
* in an unspecified state and should not be examined.
*/
static void object_array_release_entry(struct object_array_entry *ent)
{
if (ent->name != object_array_slopbuf)
free(ent->name);
free(ent->path);
}
struct object *object_array_pop(struct object_array *array)
{
struct object *ret;
if (!array->nr)
return NULL;
ret = array->objects[array->nr - 1].item;
object_array_release_entry(&array->objects[array->nr - 1]);
array->nr--;
return ret;
}
void object_array_filter(struct object_array *array,
object_array_each_func_t want, void *cb_data)
{
unsigned nr = array->nr, src, dst;
struct object_array_entry *objects = array->objects;
for (src = dst = 0; src < nr; src++) {
if (want(&objects[src], cb_data)) {
if (src != dst)
objects[dst] = objects[src];
dst++;
} else {
object_array_release_entry(&objects[src]);
}
}
array->nr = dst;
}
void object_array_clear(struct object_array *array)
{
int i;
for (i = 0; i < array->nr; i++)
object_array_release_entry(&array->objects[i]);
FREE_AND_NULL(array->objects);
array->nr = array->alloc = 0;
}
/*
* Return true if array already contains an entry.
*/
static int contains_object(struct object_array *array,
const struct object *item, const char *name)
{
unsigned nr = array->nr, i;
struct object_array_entry *object = array->objects;
for (i = 0; i < nr; i++, object++)
if (item == object->item && !strcmp(object->name, name))
return 1;
return 0;
}
void object_array_remove_duplicates(struct object_array *array)
{
unsigned nr = array->nr, src;
struct object_array_entry *objects = array->objects;
array->nr = 0;
for (src = 0; src < nr; src++) {
if (!contains_object(array, objects[src].item,
objects[src].name)) {
if (src != array->nr)
objects[array->nr] = objects[src];
array->nr++;
} else {
object_array_release_entry(&objects[src]);
}
}
}
void clear_object_flags(unsigned flags)
{
int i;
for (i=0; i < the_repository->parsed_objects->obj_hash_size; i++) {
struct object *obj = the_repository->parsed_objects->obj_hash[i];
if (obj)
obj->flags &= ~flags;
}
}
void repo_clear_commit_marks(struct repository *r, unsigned int flags)
{
int i;
for (i = 0; i < r->parsed_objects->obj_hash_size; i++) {
struct object *obj = r->parsed_objects->obj_hash[i];
if (obj && obj->type == OBJ_COMMIT)
obj->flags &= ~flags;
}
}
struct parsed_object_pool *parsed_object_pool_new(void)
{
struct parsed_object_pool *o = xmalloc(sizeof(*o));
memset(o, 0, sizeof(*o));
o->blob_state = allocate_alloc_state();
o->tree_state = allocate_alloc_state();
o->commit_state = allocate_alloc_state();
o->tag_state = allocate_alloc_state();
o->object_state = allocate_alloc_state();
o->is_shallow = -1;
CALLOC_ARRAY(o->shallow_stat, 1);
o->buffer_slab = allocate_commit_buffer_slab();
return o;
}
struct raw_object_store *raw_object_store_new(void)
{
struct raw_object_store *o = xmalloc(sizeof(*o));
memset(o, 0, sizeof(*o));
INIT_LIST_HEAD(&o->packed_git_mru);
hashmap_init(&o->pack_map, pack_map_entry_cmp, NULL, 0);
pthread_mutex_init(&o->replace_mutex, NULL);
return o;
}
void free_object_directory(struct object_directory *odb)
{
free(odb->path);
odb_clear_loose_cache(odb);
free(odb);
}
static void free_object_directories(struct raw_object_store *o)
{
while (o->odb) {
struct object_directory *next;
next = o->odb->next;
free_object_directory(o->odb);
o->odb = next;
}
kh_destroy_odb_path_map(o->odb_by_path);
o->odb_by_path = NULL;
}
void raw_object_store_clear(struct raw_object_store *o)
{
FREE_AND_NULL(o->alternate_db);
oidmap_free(o->replace_map, 1);
FREE_AND_NULL(o->replace_map);
pthread_mutex_destroy(&o->replace_mutex);
free_commit_graph(o->commit_graph);
o->commit_graph = NULL;
o->commit_graph_attempted = 0;
free_object_directories(o);
o->odb_tail = NULL;
o->loaded_alternates = 0;
INIT_LIST_HEAD(&o->packed_git_mru);
close_object_store(o);
o->packed_git = NULL;
hashmap_clear(&o->pack_map);
}
void parsed_object_pool_clear(struct parsed_object_pool *o)
{
/*
* As objects are allocated in slabs (see alloc.c), we do
* not need to free each object, but each slab instead.
*
* Before doing so, we need to free any additional memory
* the objects may hold.
*/
unsigned i;
for (i = 0; i < o->obj_hash_size; i++) {
struct object *obj = o->obj_hash[i];
if (!obj)
continue;
if (obj->type == OBJ_TREE)
free_tree_buffer((struct tree*)obj);
else if (obj->type == OBJ_COMMIT)
release_commit_memory(o, (struct commit*)obj);
else if (obj->type == OBJ_TAG)
release_tag_memory((struct tag*)obj);
}
FREE_AND_NULL(o->obj_hash);
o->obj_hash_size = 0;
free_commit_buffer_slab(o->buffer_slab);
o->buffer_slab = NULL;
clear_alloc_state(o->blob_state);
clear_alloc_state(o->tree_state);
clear_alloc_state(o->commit_state);
clear_alloc_state(o->tag_state);
clear_alloc_state(o->object_state);
stat_validity_clear(o->shallow_stat);
FREE_AND_NULL(o->blob_state);
FREE_AND_NULL(o->tree_state);
FREE_AND_NULL(o->commit_state);
FREE_AND_NULL(o->tag_state);
FREE_AND_NULL(o->object_state);
FREE_AND_NULL(o->shallow_stat);
}