git/reachable.c

221 lines
5.5 KiB
C
Raw Normal View History

#include "cache.h"
#include "refs.h"
#include "tag.h"
#include "commit.h"
#include "blob.h"
#include "diff.h"
#include "revision.h"
#include "reachable.h"
#include "cache-tree.h"
static void process_blob(struct blob *blob,
struct object_array *p,
struct name_path *path,
const char *name)
{
struct object *obj = &blob->object;
if (obj->flags & SEEN)
return;
obj->flags |= SEEN;
/* Nothing to do, really .. The blob lookup was the important part */
}
Make git-prune submodule aware (and fix a SEGFAULT in the process) I ran git-prune on a repository and got this: $ git-prune error: Object 228f8065b930120e35fc0c154c237487ab02d64a is a blob, not a commit Segmentation fault (core dumped) This repository was a strange one in that it was being used to provide its own submodule. That is, the repository was cloned into a subdirectory, an independent branch checked out in that subdirectory, and then it was marked as a submodule. git-prune then failed in the above manner. The problem was that git-prune was not submodule aware in two areas. Linus said: > So what happens is that something traverses a tree object, looks at each > entry, sees that it's not a tree, and tries to look it up as a blob. But > subprojects are commits, not blobs, and then when you look at the object > more closely, you get the above kind of object type confusion. and included a patch to add an S_ISGITLINK() test to reachable.c's process_tree() function. That fixed the first git-prune error, and stopped it from trying to process the gitlink entries in trees as if they were pointers to other trees (and of course failing, because gitlinks _aren't_ trees). That part of this patch is his. The second area is add_cache_refs(). This is called before starting the reachability analysis, and was calling lookup_blob() on every object hash found in the index. However, it is no longer true that every hash in the index is a pointer to a blob, some of them are gitlinks, and are not backed by any object at all, they are commits in another repository. Normally this bug was not causing any problems, but in the case of the self-referencing repository described above, it meant that the gitlink hash was being marked as being of type OBJ_BLOB by add_cache_refs() call to lookup_blob(). Then later, because that hash was also pointed to by a ref, add_one_ref() would treat it as a commit; lookup_commit() would return a NULL because that object was already noted as being an OBJ_BLOB, not an OBJ_COMMIT; and parse_commit_buffer() would SEGFAULT on that NULL pointer. The fix made by this patch is to not blindly call lookup_blob() in reachable.c's add_cache_refs(), and instead skip any index entries that are S_ISGITLINK(). Signed-off-by: Andy Parkins <andyparkins@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-07-02 20:56:58 +08:00
static void process_gitlink(const unsigned char *sha1,
struct object_array *p,
struct name_path *path,
const char *name)
{
/* I don't think we want to recurse into this, really. */
}
static void process_tree(struct tree *tree,
struct object_array *p,
struct name_path *path,
const char *name)
{
struct object *obj = &tree->object;
struct tree_desc desc;
struct name_entry entry;
struct name_path me;
if (obj->flags & SEEN)
return;
obj->flags |= SEEN;
if (parse_tree(tree) < 0)
die("bad tree object %s", sha1_to_hex(obj->sha1));
name = xstrdup(name);
add_object(obj, p, path, name);
me.up = path;
me.elem = name;
me.elem_len = strlen(name);
init_tree_desc(&desc, tree->buffer, tree->size);
while (tree_entry(&desc, &entry)) {
if (S_ISDIR(entry.mode))
process_tree(lookup_tree(entry.sha1), p, &me, entry.path);
else if (S_ISGITLINK(entry.mode))
Make git-prune submodule aware (and fix a SEGFAULT in the process) I ran git-prune on a repository and got this: $ git-prune error: Object 228f8065b930120e35fc0c154c237487ab02d64a is a blob, not a commit Segmentation fault (core dumped) This repository was a strange one in that it was being used to provide its own submodule. That is, the repository was cloned into a subdirectory, an independent branch checked out in that subdirectory, and then it was marked as a submodule. git-prune then failed in the above manner. The problem was that git-prune was not submodule aware in two areas. Linus said: > So what happens is that something traverses a tree object, looks at each > entry, sees that it's not a tree, and tries to look it up as a blob. But > subprojects are commits, not blobs, and then when you look at the object > more closely, you get the above kind of object type confusion. and included a patch to add an S_ISGITLINK() test to reachable.c's process_tree() function. That fixed the first git-prune error, and stopped it from trying to process the gitlink entries in trees as if they were pointers to other trees (and of course failing, because gitlinks _aren't_ trees). That part of this patch is his. The second area is add_cache_refs(). This is called before starting the reachability analysis, and was calling lookup_blob() on every object hash found in the index. However, it is no longer true that every hash in the index is a pointer to a blob, some of them are gitlinks, and are not backed by any object at all, they are commits in another repository. Normally this bug was not causing any problems, but in the case of the self-referencing repository described above, it meant that the gitlink hash was being marked as being of type OBJ_BLOB by add_cache_refs() call to lookup_blob(). Then later, because that hash was also pointed to by a ref, add_one_ref() would treat it as a commit; lookup_commit() would return a NULL because that object was already noted as being an OBJ_BLOB, not an OBJ_COMMIT; and parse_commit_buffer() would SEGFAULT on that NULL pointer. The fix made by this patch is to not blindly call lookup_blob() in reachable.c's add_cache_refs(), and instead skip any index entries that are S_ISGITLINK(). Signed-off-by: Andy Parkins <andyparkins@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-07-02 20:56:58 +08:00
process_gitlink(entry.sha1, p, &me, entry.path);
else
process_blob(lookup_blob(entry.sha1), p, &me, entry.path);
}
free(tree->buffer);
tree->buffer = NULL;
}
static void process_tag(struct tag *tag, struct object_array *p, const char *name)
{
struct object *obj = &tag->object;
struct name_path me;
if (obj->flags & SEEN)
return;
obj->flags |= SEEN;
me.up = NULL;
me.elem = "tag:/";
me.elem_len = 5;
if (parse_tag(tag) < 0)
die("bad tag object %s", sha1_to_hex(obj->sha1));
add_object(tag->tagged, p, NULL, name);
}
static void walk_commit_list(struct rev_info *revs)
{
int i;
struct commit *commit;
struct object_array objects = { 0, 0, NULL };
/* Walk all commits, process their trees */
while ((commit = get_revision(revs)) != NULL)
process_tree(commit->tree, &objects, NULL, "");
/* Then walk all the pending objects, recursively processing them too */
for (i = 0; i < revs->pending.nr; i++) {
struct object_array_entry *pending = revs->pending.objects + i;
struct object *obj = pending->item;
const char *name = pending->name;
if (obj->type == OBJ_TAG) {
process_tag((struct tag *) obj, &objects, name);
continue;
}
if (obj->type == OBJ_TREE) {
process_tree((struct tree *)obj, &objects, NULL, name);
continue;
}
if (obj->type == OBJ_BLOB) {
process_blob((struct blob *)obj, &objects, NULL, name);
continue;
}
die("unknown pending object %s (%s)", sha1_to_hex(obj->sha1), name);
}
}
static int add_one_reflog_ent(unsigned char *osha1, unsigned char *nsha1,
const char *email, unsigned long timestamp, int tz,
const char *message, void *cb_data)
{
struct object *object;
struct rev_info *revs = (struct rev_info *)cb_data;
object = parse_object(osha1);
if (object)
add_pending_object(revs, object, "");
object = parse_object(nsha1);
if (object)
add_pending_object(revs, object, "");
return 0;
}
static int add_one_ref(const char *path, const unsigned char *sha1, int flag, void *cb_data)
{
struct object *object = parse_object(sha1);
struct rev_info *revs = (struct rev_info *)cb_data;
if (!object)
die("bad object ref: %s:%s", path, sha1_to_hex(sha1));
add_pending_object(revs, object, "");
return 0;
}
static int add_one_reflog(const char *path, const unsigned char *sha1, int flag, void *cb_data)
{
for_each_reflog_ent(path, add_one_reflog_ent, cb_data);
return 0;
}
static void add_one_tree(const unsigned char *sha1, struct rev_info *revs)
{
struct tree *tree = lookup_tree(sha1);
add_pending_object(revs, &tree->object, "");
}
static void add_cache_tree(struct cache_tree *it, struct rev_info *revs)
{
int i;
if (it->entry_count >= 0)
add_one_tree(it->sha1, revs);
for (i = 0; i < it->subtree_nr; i++)
add_cache_tree(it->down[i]->cache_tree, revs);
}
static void add_cache_refs(struct rev_info *revs)
{
int i;
read_cache();
for (i = 0; i < active_nr; i++) {
Make git-prune submodule aware (and fix a SEGFAULT in the process) I ran git-prune on a repository and got this: $ git-prune error: Object 228f8065b930120e35fc0c154c237487ab02d64a is a blob, not a commit Segmentation fault (core dumped) This repository was a strange one in that it was being used to provide its own submodule. That is, the repository was cloned into a subdirectory, an independent branch checked out in that subdirectory, and then it was marked as a submodule. git-prune then failed in the above manner. The problem was that git-prune was not submodule aware in two areas. Linus said: > So what happens is that something traverses a tree object, looks at each > entry, sees that it's not a tree, and tries to look it up as a blob. But > subprojects are commits, not blobs, and then when you look at the object > more closely, you get the above kind of object type confusion. and included a patch to add an S_ISGITLINK() test to reachable.c's process_tree() function. That fixed the first git-prune error, and stopped it from trying to process the gitlink entries in trees as if they were pointers to other trees (and of course failing, because gitlinks _aren't_ trees). That part of this patch is his. The second area is add_cache_refs(). This is called before starting the reachability analysis, and was calling lookup_blob() on every object hash found in the index. However, it is no longer true that every hash in the index is a pointer to a blob, some of them are gitlinks, and are not backed by any object at all, they are commits in another repository. Normally this bug was not causing any problems, but in the case of the self-referencing repository described above, it meant that the gitlink hash was being marked as being of type OBJ_BLOB by add_cache_refs() call to lookup_blob(). Then later, because that hash was also pointed to by a ref, add_one_ref() would treat it as a commit; lookup_commit() would return a NULL because that object was already noted as being an OBJ_BLOB, not an OBJ_COMMIT; and parse_commit_buffer() would SEGFAULT on that NULL pointer. The fix made by this patch is to not blindly call lookup_blob() in reachable.c's add_cache_refs(), and instead skip any index entries that are S_ISGITLINK(). Signed-off-by: Andy Parkins <andyparkins@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-07-02 20:56:58 +08:00
/*
* The index can contain blobs and GITLINKs, GITLINKs are hashes
* that don't actually point to objects in the repository, it's
* almost guaranteed that they are NOT blobs, so we don't call
* lookup_blob() on them, to avoid populating the hash table
* with invalid information
*/
if (S_ISGITLINK(active_cache[i]->ce_mode))
Make git-prune submodule aware (and fix a SEGFAULT in the process) I ran git-prune on a repository and got this: $ git-prune error: Object 228f8065b930120e35fc0c154c237487ab02d64a is a blob, not a commit Segmentation fault (core dumped) This repository was a strange one in that it was being used to provide its own submodule. That is, the repository was cloned into a subdirectory, an independent branch checked out in that subdirectory, and then it was marked as a submodule. git-prune then failed in the above manner. The problem was that git-prune was not submodule aware in two areas. Linus said: > So what happens is that something traverses a tree object, looks at each > entry, sees that it's not a tree, and tries to look it up as a blob. But > subprojects are commits, not blobs, and then when you look at the object > more closely, you get the above kind of object type confusion. and included a patch to add an S_ISGITLINK() test to reachable.c's process_tree() function. That fixed the first git-prune error, and stopped it from trying to process the gitlink entries in trees as if they were pointers to other trees (and of course failing, because gitlinks _aren't_ trees). That part of this patch is his. The second area is add_cache_refs(). This is called before starting the reachability analysis, and was calling lookup_blob() on every object hash found in the index. However, it is no longer true that every hash in the index is a pointer to a blob, some of them are gitlinks, and are not backed by any object at all, they are commits in another repository. Normally this bug was not causing any problems, but in the case of the self-referencing repository described above, it meant that the gitlink hash was being marked as being of type OBJ_BLOB by add_cache_refs() call to lookup_blob(). Then later, because that hash was also pointed to by a ref, add_one_ref() would treat it as a commit; lookup_commit() would return a NULL because that object was already noted as being an OBJ_BLOB, not an OBJ_COMMIT; and parse_commit_buffer() would SEGFAULT on that NULL pointer. The fix made by this patch is to not blindly call lookup_blob() in reachable.c's add_cache_refs(), and instead skip any index entries that are S_ISGITLINK(). Signed-off-by: Andy Parkins <andyparkins@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-07-02 20:56:58 +08:00
continue;
lookup_blob(active_cache[i]->sha1);
/*
* We could add the blobs to the pending list, but quite
* frankly, we don't care. Once we've looked them up, and
* added them as objects, we've really done everything
* there is to do for a blob
*/
}
if (active_cache_tree)
add_cache_tree(active_cache_tree, revs);
}
void mark_reachable_objects(struct rev_info *revs, int mark_reflog)
{
/*
* Set up revision parsing, and mark us as being interested
* in all object types, not just commits.
*/
revs->tag_objects = 1;
revs->blob_objects = 1;
revs->tree_objects = 1;
/* Add all refs from the index file */
add_cache_refs(revs);
/* Add all external refs */
for_each_ref(add_one_ref, revs);
/* Add all reflog info */
if (mark_reflog)
for_each_reflog(add_one_reflog, revs);
/*
* Set up the revision walk - this will move all commits
* from the pending list to the commit walking list.
*/
prepare_revision_walk(revs);
walk_commit_list(revs);
}