git-commit-vandalism/repository.c

284 lines
6.7 KiB
C
Raw Normal View History

/*
* not really _using_ the compat macros, just make sure the_index
* declaration matches the definition in this file.
*/
#define USE_THE_INDEX_COMPATIBILITY_MACROS
#include "cache.h"
#include "repository.h"
#include "object-store.h"
#include "config.h"
#include "object.h"
#include "lockfile.h"
#include "submodule-config.h"
/* The main repository */
static struct repository the_repo;
struct repository *the_repository;
struct index_state the_index;
void initialize_the_repository(void)
{
the_repository = &the_repo;
the_repo.index = &the_index;
the_repo.objects = raw_object_store_new();
the_repo.parsed_objects = parsed_object_pool_new();
repo_set_hash_algo(&the_repo, GIT_HASH_SHA1);
}
static void expand_base_dir(char **out, const char *in,
const char *base_dir, const char *def_in)
{
free(*out);
if (in)
*out = xstrdup(in);
else
*out = xstrfmt("%s/%s", base_dir, def_in);
}
static void repo_set_commondir(struct repository *repo,
const char *commondir)
{
struct strbuf sb = STRBUF_INIT;
free(repo->commondir);
if (commondir) {
repo->different_commondir = 1;
repo->commondir = xstrdup(commondir);
return;
}
repo->different_commondir = get_common_dir_noenv(&sb, repo->gitdir);
repo->commondir = strbuf_detach(&sb, NULL);
}
void repo_set_gitdir(struct repository *repo,
const char *root,
const struct set_gitdir_args *o)
{
const char *gitfile = read_gitfile(root);
/*
* repo->gitdir is saved because the caller could pass "root"
* that also points to repo->gitdir. We want to keep it alive
* until after xstrdup(root). Then we can free it.
*/
char *old_gitdir = repo->gitdir;
repo->gitdir = xstrdup(gitfile ? gitfile : root);
free(old_gitdir);
repo_set_commondir(repo, o->commondir);
sha1-file: use an object_directory for the main object dir Our handling of alternate object directories is needlessly different from the main object directory. As a result, many places in the code basically look like this: do_something(r->objects->objdir); for (odb = r->objects->alt_odb_list; odb; odb = odb->next) do_something(odb->path); That gets annoying when do_something() is non-trivial, and we've resorted to gross hacks like creating fake alternates (see find_short_object_filename()). Instead, let's give each raw_object_store a unified list of object_directory structs. The first will be the main store, and everything after is an alternate. Very few callers even care about the distinction, and can just loop over the whole list (and those who care can just treat the first element differently). A few observations: - we don't need r->objects->objectdir anymore, and can just mechanically convert that to r->objects->odb->path - object_directory's path field needs to become a real pointer rather than a FLEX_ARRAY, in order to fill it with expand_base_dir() - we'll call prepare_alt_odb() earlier in many functions (i.e., outside of the loop). This may result in us calling it even when our function would be satisfied looking only at the main odb. But this doesn't matter in practice. It's not a very expensive operation in the first place, and in the majority of cases it will be a noop. We call it already (and cache its results) in prepare_packed_git(), and we'll generally check packs before loose objects. So essentially every program is going to call it immediately once per program. Arguably we should just prepare_alt_odb() immediately upon setting up the repository's object directory, which would save us sprinkling calls throughout the code base (and forgetting to do so has been a source of subtle bugs in the past). But I've stopped short of that here, since there are already a lot of other moving parts in this patch. - Most call sites just get shorter. The check_and_freshen() functions are an exception, because they have entry points to handle local and nonlocal directories separately. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-11-12 15:50:39 +01:00
if (!repo->objects->odb) {
repo->objects->odb = xcalloc(1, sizeof(*repo->objects->odb));
repo->objects->odb_tail = &repo->objects->odb->next;
}
expand_base_dir(&repo->objects->odb->path, o->object_dir,
repo->commondir, "objects");
sha1-file: use an object_directory for the main object dir Our handling of alternate object directories is needlessly different from the main object directory. As a result, many places in the code basically look like this: do_something(r->objects->objdir); for (odb = r->objects->alt_odb_list; odb; odb = odb->next) do_something(odb->path); That gets annoying when do_something() is non-trivial, and we've resorted to gross hacks like creating fake alternates (see find_short_object_filename()). Instead, let's give each raw_object_store a unified list of object_directory structs. The first will be the main store, and everything after is an alternate. Very few callers even care about the distinction, and can just loop over the whole list (and those who care can just treat the first element differently). A few observations: - we don't need r->objects->objectdir anymore, and can just mechanically convert that to r->objects->odb->path - object_directory's path field needs to become a real pointer rather than a FLEX_ARRAY, in order to fill it with expand_base_dir() - we'll call prepare_alt_odb() earlier in many functions (i.e., outside of the loop). This may result in us calling it even when our function would be satisfied looking only at the main odb. But this doesn't matter in practice. It's not a very expensive operation in the first place, and in the majority of cases it will be a noop. We call it already (and cache its results) in prepare_packed_git(), and we'll generally check packs before loose objects. So essentially every program is going to call it immediately once per program. Arguably we should just prepare_alt_odb() immediately upon setting up the repository's object directory, which would save us sprinkling calls throughout the code base (and forgetting to do so has been a source of subtle bugs in the past). But I've stopped short of that here, since there are already a lot of other moving parts in this patch. - Most call sites just get shorter. The check_and_freshen() functions are an exception, because they have entry points to handle local and nonlocal directories separately. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-11-12 15:50:39 +01:00
free(repo->objects->alternate_db);
repo->objects->alternate_db = xstrdup_or_null(o->alternate_db);
expand_base_dir(&repo->graft_file, o->graft_file,
repo->commondir, "info/grafts");
expand_base_dir(&repo->index_file, o->index_file,
repo->gitdir, "index");
}
void repo_set_hash_algo(struct repository *repo, int hash_algo)
{
repo->hash_algo = &hash_algos[hash_algo];
}
/*
* Attempt to resolve and set the provided 'gitdir' for repository 'repo'.
* Return 0 upon success and a non-zero value upon failure.
*/
static int repo_init_gitdir(struct repository *repo, const char *gitdir)
{
int ret = 0;
int error = 0;
char *abspath = NULL;
const char *resolved_gitdir;
struct set_gitdir_args args = { NULL };
abspath = real_pathdup(gitdir, 0);
if (!abspath) {
ret = -1;
goto out;
}
/* 'gitdir' must reference the gitdir directly */
resolved_gitdir = resolve_gitdir_gently(abspath, &error);
if (!resolved_gitdir) {
ret = -1;
goto out;
}
repo_set_gitdir(repo, resolved_gitdir, &args);
out:
free(abspath);
return ret;
}
void repo_set_worktree(struct repository *repo, const char *path)
{
repo->worktree = real_pathdup(path, 1);
trace2_def_repo(repo);
}
static int read_and_verify_repository_format(struct repository_format *format,
const char *commondir)
{
int ret = 0;
struct strbuf sb = STRBUF_INIT;
strbuf_addf(&sb, "%s/config", commondir);
read_repository_format(format, sb.buf);
strbuf_reset(&sb);
if (verify_repository_format(format, &sb) < 0) {
warning("%s", sb.buf);
ret = -1;
}
strbuf_release(&sb);
return ret;
}
/*
* Initialize 'repo' based on the provided 'gitdir'.
* Return 0 upon success and a non-zero value upon failure.
*/
int repo_init(struct repository *repo,
const char *gitdir,
const char *worktree)
{
setup: fix memory leaks with `struct repository_format` After we set up a `struct repository_format`, it owns various pieces of allocated memory. We then either use those members, because we decide we want to use the "candidate" repository format, or we discard the candidate / scratch space. In the first case, we transfer ownership of the memory to a few global variables. In the latter case, we just silently drop the struct and end up leaking memory. Introduce an initialization macro `REPOSITORY_FORMAT_INIT` and a function `clear_repository_format()`, to be used on each side of `read_repository_format()`. To have a clear and simple memory ownership, let all users of `struct repository_format` duplicate the strings that they take from it, rather than stealing the pointers. Call `clear_...()` at the start of `read_...()` instead of just zeroing the struct, since we sometimes enter the function multiple times. Thus, it is important to initialize the struct before calling `read_...()`, so document that. It's also important because we might not even call `read_...()` before we call `clear_...()`, see, e.g., builtin/init-db.c. Teach `read_...()` to clear the struct on error, so that it is reset to a safe state, and document this. (In `setup_git_directory_gently()`, we look at `repo_fmt.hash_algo` even if `repo_fmt.version` is -1, which we weren't actually supposed to do per the API. After this commit, that's ok.) We inherit the existing code's combining "error" and "no version found". Both are signalled through `version == -1` and now both cause us to clear any partial configuration we have picked up. For "extensions.*", that's fine, since they require a positive version number. For "core.bare" and "core.worktree", we're already verifying that we have a non-negative version number before using them. Signed-off-by: Martin Ågren <martin.agren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-02-28 21:36:28 +01:00
struct repository_format format = REPOSITORY_FORMAT_INIT;
memset(repo, 0, sizeof(*repo));
repo->objects = raw_object_store_new();
repo->parsed_objects = parsed_object_pool_new();
if (repo_init_gitdir(repo, gitdir))
goto error;
if (read_and_verify_repository_format(&format, repo->commondir))
goto error;
repo_set_hash_algo(repo, format.hash_algo);
if (worktree)
repo_set_worktree(repo, worktree);
setup: fix memory leaks with `struct repository_format` After we set up a `struct repository_format`, it owns various pieces of allocated memory. We then either use those members, because we decide we want to use the "candidate" repository format, or we discard the candidate / scratch space. In the first case, we transfer ownership of the memory to a few global variables. In the latter case, we just silently drop the struct and end up leaking memory. Introduce an initialization macro `REPOSITORY_FORMAT_INIT` and a function `clear_repository_format()`, to be used on each side of `read_repository_format()`. To have a clear and simple memory ownership, let all users of `struct repository_format` duplicate the strings that they take from it, rather than stealing the pointers. Call `clear_...()` at the start of `read_...()` instead of just zeroing the struct, since we sometimes enter the function multiple times. Thus, it is important to initialize the struct before calling `read_...()`, so document that. It's also important because we might not even call `read_...()` before we call `clear_...()`, see, e.g., builtin/init-db.c. Teach `read_...()` to clear the struct on error, so that it is reset to a safe state, and document this. (In `setup_git_directory_gently()`, we look at `repo_fmt.hash_algo` even if `repo_fmt.version` is -1, which we weren't actually supposed to do per the API. After this commit, that's ok.) We inherit the existing code's combining "error" and "no version found". Both are signalled through `version == -1` and now both cause us to clear any partial configuration we have picked up. For "extensions.*", that's fine, since they require a positive version number. For "core.bare" and "core.worktree", we're already verifying that we have a non-negative version number before using them. Signed-off-by: Martin Ågren <martin.agren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-02-28 21:36:28 +01:00
clear_repository_format(&format);
return 0;
error:
repo_clear(repo);
return -1;
}
int repo_submodule_init(struct repository *subrepo,
struct repository *superproject,
const struct submodule *sub)
{
struct strbuf gitdir = STRBUF_INIT;
struct strbuf worktree = STRBUF_INIT;
int ret = 0;
if (!sub) {
ret = -1;
goto out;
}
strbuf_repo_worktree_path(&gitdir, superproject, "%s/.git", sub->path);
strbuf_repo_worktree_path(&worktree, superproject, "%s", sub->path);
if (repo_init(subrepo, gitdir.buf, worktree.buf)) {
/*
* If initialization fails then it may be due to the submodule
* not being populated in the superproject's worktree. Instead
* we can try to initialize the submodule by finding it's gitdir
* in the superproject's 'modules' directory. In this case the
* submodule would not have a worktree.
*/
strbuf_reset(&gitdir);
strbuf_repo_git_path(&gitdir, superproject,
"modules/%s", sub->name);
if (repo_init(subrepo, gitdir.buf, NULL)) {
ret = -1;
goto out;
}
}
subrepo->submodule_prefix = xstrfmt("%s%s/",
superproject->submodule_prefix ?
superproject->submodule_prefix :
"", sub->path);
out:
strbuf_release(&gitdir);
strbuf_release(&worktree);
return ret;
}
void repo_clear(struct repository *repo)
{
FREE_AND_NULL(repo->gitdir);
FREE_AND_NULL(repo->commondir);
FREE_AND_NULL(repo->graft_file);
FREE_AND_NULL(repo->index_file);
FREE_AND_NULL(repo->worktree);
FREE_AND_NULL(repo->submodule_prefix);
raw_object_store_clear(repo->objects);
FREE_AND_NULL(repo->objects);
parsed_object_pool_clear(repo->parsed_objects);
FREE_AND_NULL(repo->parsed_objects);
if (repo->config) {
git_configset_clear(repo->config);
FREE_AND_NULL(repo->config);
}
if (repo->submodule_cache) {
submodule_cache_free(repo->submodule_cache);
repo->submodule_cache = NULL;
}
if (repo->index) {
discard_index(repo->index);
if (repo->index != &the_index)
FREE_AND_NULL(repo->index);
}
}
int repo_read_index(struct repository *repo)
{
if (!repo->index)
repo->index = xcalloc(1, sizeof(*repo->index));
/* Complete the double-reference */
if (!repo->index->repo)
repo->index->repo = repo;
else if (repo->index->repo != repo)
BUG("repo's index should point back at itself");
read-cache: fix reading the shared index for other repos read_index_from() takes a path argument for the location of the index file. For reading the shared index in split index mode however it just ignores that path argument, and reads it from the gitdir of the current repository. This works as long as an index in the_repository is read. Once that changes, such as when we read the index of a submodule, or of a different working tree than the current one, the gitdir of the_repository will no longer contain the appropriate shared index, and git will fail to read it. For example t3007-ls-files-recurse-submodules.sh was broken with GIT_TEST_SPLIT_INDEX set in 188dce131f ("ls-files: use repository object", 2017-06-22), and t7814-grep-recurse-submodules.sh was also broken in a similar manner, probably by introducing struct repository there, although I didn't track down the exact commit for that. be489d02d2 ("revision.c: --indexed-objects add objects from all worktrees", 2017-08-23) breaks with split index mode in a similar manner, not erroring out when it can't read the index, but instead carrying on with pruning, without taking the index of the worktree into account. Fix this by passing an additional gitdir parameter to read_index_from, to indicate where it should look for and read the shared index from. read_cache_from() defaults to using the gitdir of the_repository. As it is mostly a convenience macro, having to pass get_git_dir() for every call seems overkill, and if necessary users can have more control by using read_index_from(). Helped-by: Brandon Williams <bmwill@google.com> Signed-off-by: Thomas Gummerer <t.gummerer@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-01-07 23:30:13 +01:00
return read_index_from(repo->index, repo->index_file, repo->gitdir);
}
int repo_hold_locked_index(struct repository *repo,
struct lock_file *lf,
int flags)
{
if (!repo->index_file)
BUG("the repo hasn't been setup");
return hold_lock_file_for_update(lf, repo->index_file, flags);
}