memset(&opts, 0, sizeof opts);
opts.update = 1;
opts.merge = 1;
+ opts.clone = 1;
opts.fn = oneway_merge;
opts.verbose_update = (option_verbosity >= 0);
opts.src_index = &the_index;
if (!err && (option_recurse_submodules.nr > 0)) {
struct argv_array args = ARGV_ARRAY_INIT;
- argv_array_pushl(&args, "submodule", "update", "--init", "--recursive", NULL);
+ argv_array_pushl(&args, "submodule", "update", "--require-init", "--recursive", NULL);
if (option_shallow_submodules == 1)
argv_array_push(&args, "--depth=1");
#include "diffcore.h"
#include "diff.h"
#include "object-store.h"
+ #include "dir.h"
#define OPT_QUIET (1 << 0)
#define OPT_CACHED (1 << 1)
return 0;
}
+static char *compute_submodule_clone_url(const char *rel_url)
+{
+ char *remoteurl, *relurl;
+ char *remote = get_default_remote();
+ struct strbuf remotesb = STRBUF_INIT;
+
+ strbuf_addf(&remotesb, "remote.%s.url", remote);
+ if (git_config_get_string(remotesb.buf, &remoteurl)) {
+ warning(_("could not look up configuration '%s'. Assuming this repository is its own authoritative upstream."), remotesb.buf);
+ remoteurl = xgetcwd();
+ }
+ relurl = relative_url(remoteurl, rel_url, NULL);
+
+ free(remote);
+ free(remoteurl);
+ strbuf_release(&remotesb);
+
+ return relurl;
+}
+
struct init_cb {
const char *prefix;
unsigned int flags;
/* Possibly a url relative to parent */
if (starts_with_dot_dot_slash(url) ||
starts_with_dot_slash(url)) {
- char *remoteurl, *relurl;
- char *remote = get_default_remote();
- struct strbuf remotesb = STRBUF_INIT;
- strbuf_addf(&remotesb, "remote.%s.url", remote);
- free(remote);
-
- if (git_config_get_string(remotesb.buf, &remoteurl)) {
- warning(_("could not lookup configuration '%s'. Assuming this repository is its own authoritative upstream."), remotesb.buf);
- remoteurl = xgetcwd();
- }
- relurl = relative_url(remoteurl, url, NULL);
- strbuf_release(&remotesb);
- free(remoteurl);
- free(url);
- url = relurl;
+ char *oldurl = url;
+ url = compute_submodule_clone_url(oldurl);
+ free(oldurl);
}
if (git_config_set_gently(sb.buf, url))
path, NULL);
git_config(git_diff_basic_config, NULL);
- init_revisions(&rev, prefix);
+ repo_init_revisions(the_repository, &rev, prefix);
rev.abbrev = 0;
diff_files_args.argc = setup_revisions(diff_files_args.argc,
diff_files_args.argv,
char *p, *path = NULL, *sm_gitdir;
struct strbuf sb = STRBUF_INIT;
struct string_list reference = STRING_LIST_INIT_NODUP;
- int dissociate = 0;
+ int dissociate = 0, require_init = 0;
char *sm_alternate = NULL, *error_strategy = NULL;
struct option module_clone_options[] = {
OPT__QUIET(&quiet, "Suppress output for cloning a submodule"),
OPT_BOOL(0, "progress", &progress,
N_("force cloning progress")),
+ OPT_BOOL(0, "require-init", &require_init,
+ N_("disallow cloning into non-empty directory")),
OPT_END()
};
} else
path = xstrdup(path);
+ if (validate_submodule_git_dir(sm_gitdir, name) < 0)
+ die(_("refusing to create/use '%s' in another submodule's "
+ "git dir"), sm_gitdir);
+
if (!file_exists(sm_gitdir)) {
if (safe_create_leading_directories_const(sm_gitdir) < 0)
die(_("could not create directory '%s'"), sm_gitdir);
die(_("clone of '%s' into submodule path '%s' failed"),
url, path);
} else {
+ if (require_init && !access(path, X_OK) && !is_empty_dir(path))
+ die(_("directory not empty: '%s'"), path);
if (safe_create_leading_directories_const(path) < 0)
die(_("could not create directory '%s'"), path);
strbuf_addf(&sb, "%s/index", sm_gitdir);
return 0;
}
+static void determine_submodule_update_strategy(struct repository *r,
+ int just_cloned,
+ const char *path,
+ const char *update,
+ struct submodule_update_strategy *out)
+{
+ const struct submodule *sub = submodule_from_path(r, &null_oid, path);
+ char *key;
+ const char *val;
+
+ key = xstrfmt("submodule.%s.update", sub->name);
+
+ if (update) {
+ if (parse_submodule_update_strategy(update, out) < 0)
+ die(_("Invalid update mode '%s' for submodule path '%s'"),
+ update, path);
+ } else if (!repo_config_get_string_const(r, key, &val)) {
+ if (parse_submodule_update_strategy(val, out) < 0)
+ die(_("Invalid update mode '%s' configured for submodule path '%s'"),
+ val, path);
+ } else if (sub->update_strategy.type != SM_UPDATE_UNSPECIFIED) {
+ out->type = sub->update_strategy.type;
+ out->command = sub->update_strategy.command;
+ } else
+ out->type = SM_UPDATE_CHECKOUT;
+
+ if (just_cloned &&
+ (out->type == SM_UPDATE_MERGE ||
+ out->type == SM_UPDATE_REBASE ||
+ out->type == SM_UPDATE_NONE))
+ out->type = SM_UPDATE_CHECKOUT;
+
+ free(key);
+}
+
+static int module_update_module_mode(int argc, const char **argv, const char *prefix)
+{
+ const char *path, *update = NULL;
+ int just_cloned;
+ struct submodule_update_strategy update_strategy = { .type = SM_UPDATE_CHECKOUT };
+
+ if (argc < 3 || argc > 4)
+ die("submodule--helper update-module-clone expects <just-cloned> <path> [<update>]");
+
+ just_cloned = git_config_int("just_cloned", argv[1]);
+ path = argv[2];
+
+ if (argc == 4)
+ update = argv[3];
+
+ determine_submodule_update_strategy(the_repository,
+ just_cloned, path, update,
+ &update_strategy);
+ fputs(submodule_strategy_to_string(&update_strategy), stdout);
+
+ return 0;
+}
+
+struct update_clone_data {
+ const struct submodule *sub;
+ struct object_id oid;
+ unsigned just_cloned;
+};
+
struct submodule_update_clone {
/* index into 'list', the list of submodules to look into for cloning */
int current;
int recommend_shallow;
struct string_list references;
int dissociate;
+ unsigned require_init;
const char *depth;
const char *recursive_prefix;
const char *prefix;
- /* Machine-readable status lines to be consumed by git-submodule.sh */
- struct string_list projectlines;
+ /* to be consumed by git-submodule.sh */
+ struct update_clone_data *update_clone;
+ int update_clone_nr; int update_clone_alloc;
/* If we want to stop as fast as possible and return an error */
unsigned quickstop : 1;
/* failed clones to be retried again */
const struct cache_entry **failed_clones;
int failed_clones_nr, failed_clones_alloc;
+
+ int max_jobs;
};
#define SUBMODULE_UPDATE_CLONE_INIT {0, MODULE_LIST_INIT, 0, \
- SUBMODULE_UPDATE_STRATEGY_INIT, 0, 0, -1, STRING_LIST_INIT_DUP, 0, \
+ SUBMODULE_UPDATE_STRATEGY_INIT, 0, 0, -1, STRING_LIST_INIT_DUP, 0, 0, \
NULL, NULL, NULL, \
- STRING_LIST_INIT_DUP, 0, NULL, 0, 0}
+ NULL, 0, 0, 0, NULL, 0, 0, 0}
static void next_submodule_warn_missing(struct submodule_update_clone *suc,
struct strbuf sb = STRBUF_INIT;
const char *displaypath = NULL;
int needs_cloning = 0;
+ int need_free_url = 0;
if (ce_stage(ce)) {
if (suc->recursive_prefix)
strbuf_reset(&sb);
strbuf_addf(&sb, "submodule.%s.url", sub->name);
- if (repo_config_get_string_const(the_repository, sb.buf, &url))
- url = sub->url;
+ if (repo_config_get_string_const(the_repository, sb.buf, &url)) {
+ if (starts_with_dot_slash(sub->url) ||
+ starts_with_dot_dot_slash(sub->url)) {
+ url = compute_submodule_clone_url(sub->url);
+ need_free_url = 1;
+ } else
+ url = sub->url;
+ }
strbuf_reset(&sb);
strbuf_addf(&sb, "%s/.git", ce->name);
needs_cloning = !file_exists(sb.buf);
- strbuf_reset(&sb);
- strbuf_addf(&sb, "%06o %s %d %d\t%s\n", ce->ce_mode,
- oid_to_hex(&ce->oid), ce_stage(ce),
- needs_cloning, ce->name);
- string_list_append(&suc->projectlines, sb.buf);
+ ALLOC_GROW(suc->update_clone, suc->update_clone_nr + 1,
+ suc->update_clone_alloc);
+ oidcpy(&suc->update_clone[suc->update_clone_nr].oid, &ce->oid);
+ suc->update_clone[suc->update_clone_nr].just_cloned = needs_cloning;
+ suc->update_clone[suc->update_clone_nr].sub = sub;
+ suc->update_clone_nr++;
if (!needs_cloning)
goto cleanup;
argv_array_pushl(&child->args, "--prefix", suc->prefix, NULL);
if (suc->recommend_shallow && sub->recommend_shallow == 1)
argv_array_push(&child->args, "--depth=1");
+ if (suc->require_init)
+ argv_array_push(&child->args, "--require-init");
argv_array_pushl(&child->args, "--path", sub->path, NULL);
argv_array_pushl(&child->args, "--name", sub->name, NULL);
argv_array_pushl(&child->args, "--url", url, NULL);
cleanup:
strbuf_reset(&displaypath_sb);
strbuf_reset(&sb);
+ if (need_free_url)
+ free((void*)url);
return needs_cloning;
}
return 0;
}
+static void update_submodule(struct update_clone_data *ucd)
+{
+ fprintf(stdout, "dummy %s %d\t%s\n",
+ oid_to_hex(&ucd->oid),
+ ucd->just_cloned,
+ ucd->sub->path);
+}
+
+static int update_submodules(struct submodule_update_clone *suc)
+{
+ int i;
+
+ run_processes_parallel(suc->max_jobs,
+ update_clone_get_next_task,
+ update_clone_start_failure,
+ update_clone_task_finished,
+ suc);
+
+ /*
+ * We saved the output and put it out all at once now.
+ * That means:
+ * - the listener does not have to interleave their (checkout)
+ * work with our fetching. The writes involved in a
+ * checkout involve more straightforward sequential I/O.
+ * - the listener can avoid doing any work if fetching failed.
+ */
+ if (suc->quickstop)
+ return 1;
+
+ for (i = 0; i < suc->update_clone_nr; i++)
+ update_submodule(&suc->update_clone[i]);
+
+ return 0;
+}
+
static int update_clone(int argc, const char **argv, const char *prefix)
{
const char *update = NULL;
- int max_jobs = 1;
- struct string_list_item *item;
struct pathspec pathspec;
struct submodule_update_clone suc = SUBMODULE_UPDATE_CLONE_INIT;
OPT_STRING(0, "depth", &suc.depth, "<depth>",
N_("Create a shallow clone truncated to the "
"specified number of revisions")),
- OPT_INTEGER('j', "jobs", &max_jobs,
+ OPT_INTEGER('j', "jobs", &suc.max_jobs,
N_("parallel jobs")),
OPT_BOOL(0, "recommend-shallow", &suc.recommend_shallow,
N_("whether the initial clone should follow the shallow recommendation")),
OPT__QUIET(&suc.quiet, N_("don't print cloning progress")),
OPT_BOOL(0, "progress", &suc.progress,
N_("force cloning progress")),
+ OPT_BOOL(0, "require-init", &suc.require_init,
+ N_("disallow cloning into non-empty directory")),
OPT_END()
};
};
suc.prefix = prefix;
- update_clone_config_from_gitmodules(&max_jobs);
- git_config(git_update_clone_config, &max_jobs);
+ update_clone_config_from_gitmodules(&suc.max_jobs);
+ git_config(git_update_clone_config, &suc.max_jobs);
argc = parse_options(argc, argv, prefix, module_update_clone_options,
git_submodule_helper_usage, 0);
if (pathspec.nr)
suc.warn_if_uninitialized = 1;
- run_processes_parallel(max_jobs,
- update_clone_get_next_task,
- update_clone_start_failure,
- update_clone_task_finished,
- &suc);
-
- /*
- * We saved the output and put it out all at once now.
- * That means:
- * - the listener does not have to interleave their (checkout)
- * work with our fetching. The writes involved in a
- * checkout involve more straightforward sequential I/O.
- * - the listener can avoid doing any work if fetching failed.
- */
- if (suc.quickstop)
- return 1;
-
- for_each_string_list_item(item, &suc.projectlines)
- fprintf(stdout, "%s", item->string);
-
- return 0;
+ return update_submodules(&suc);
}
static int resolve_relative_path(int argc, const char **argv, const char *prefix)
return 0;
}
+static int ensure_core_worktree(int argc, const char **argv, const char *prefix)
+{
+ const struct submodule *sub;
+ const char *path;
+ char *cw;
+ struct repository subrepo;
+
+ if (argc != 2)
+ BUG("submodule--helper connect-gitdir-workingtree <name> <path>");
+
+ path = argv[1];
+
+ sub = submodule_from_path(the_repository, &null_oid, path);
+ if (!sub)
+ BUG("We could get the submodule handle before?");
+
+ if (repo_submodule_init(&subrepo, the_repository, path))
+ die(_("could not get a repository handle for submodule '%s'"), path);
+
+ if (!repo_config_get_string(&subrepo, "core.worktree", &cw)) {
+ char *cfg_file, *abs_path;
+ const char *rel_path;
+ struct strbuf sb = STRBUF_INIT;
+
+ cfg_file = repo_git_path(&subrepo, "config");
+
+ abs_path = absolute_pathdup(path);
+ rel_path = relative_path(abs_path, subrepo.gitdir, &sb);
+
+ git_config_set_in_file(cfg_file, "core.worktree", rel_path);
+
+ free(cfg_file);
+ free(abs_path);
+ strbuf_release(&sb);
+ }
+
+ return 0;
+}
+
static int absorb_git_dirs(int argc, const char **argv, const char *prefix)
{
int i;
return 0;
}
+static int module_config(int argc, const char **argv, const char *prefix)
+{
+ enum {
+ CHECK_WRITEABLE = 1
+ } command = 0;
+
+ struct option module_config_options[] = {
+ OPT_CMDMODE(0, "check-writeable", &command,
+ N_("check if it is safe to write to the .gitmodules file"),
+ CHECK_WRITEABLE),
+ OPT_END()
+ };
+ const char *const git_submodule_helper_usage[] = {
+ N_("git submodule--helper config name [value]"),
+ N_("git submodule--helper config --check-writeable"),
+ NULL
+ };
+
+ argc = parse_options(argc, argv, prefix, module_config_options,
+ git_submodule_helper_usage, PARSE_OPT_KEEP_ARGV0);
+
+ if (argc == 1 && command == CHECK_WRITEABLE)
+ return is_writing_gitmodules_ok() ? 0 : -1;
+
+ /* Equivalent to ACTION_GET in builtin/config.c */
+ if (argc == 2)
+ return print_config_from_gitmodules(the_repository, argv[1]);
+
+ /* Equivalent to ACTION_SET in builtin/config.c */
+ if (argc == 3) {
+ if (!is_writing_gitmodules_ok())
+ die(_("please make sure that the .gitmodules file is in the working tree"));
+
+ return config_set_in_gitmodules_file_gently(argv[1], argv[2]);
+ }
+
+ usage_with_options(git_submodule_helper_usage, module_config_options);
+}
+
#define SUPPORT_SUPER_PREFIX (1<<0)
struct cmd_struct {
{"list", module_list, 0},
{"name", module_name, 0},
{"clone", module_clone, 0},
+ {"update-module-mode", module_update_module_mode, 0},
{"update-clone", update_clone, 0},
+ {"ensure-core-worktree", ensure_core_worktree, 0},
{"relative-path", resolve_relative_path, 0},
{"resolve-relative-url", resolve_relative_url, 0},
{"resolve-relative-url-test", resolve_relative_url_test, 0},
{"absorb-git-dirs", absorb_git_dirs, SUPPORT_SUPER_PREFIX},
{"is-active", is_active, 0},
{"check-name", check_name, 0},
+ {"config", module_config, 0},
};
int cmd_submodule__helper(int argc, const char **argv, const char *prefix)
#include "../strbuf.h"
#include "../run-command.h"
#include "../cache.h"
+#include "win32/lazyload.h"
+#include "../config.h"
#define HCAST(type, handle) ((type)(intptr_t)handle)
}
}
+/* Windows only */
+enum hide_dotfiles_type {
+ HIDE_DOTFILES_FALSE = 0,
+ HIDE_DOTFILES_TRUE,
+ HIDE_DOTFILES_DOTGITONLY
+};
+
+static enum hide_dotfiles_type hide_dotfiles = HIDE_DOTFILES_DOTGITONLY;
+static char *unset_environment_variables;
+
+int mingw_core_config(const char *var, const char *value, void *cb)
+{
+ if (!strcmp(var, "core.hidedotfiles")) {
+ if (value && !strcasecmp(value, "dotgitonly"))
+ hide_dotfiles = HIDE_DOTFILES_DOTGITONLY;
+ else
+ hide_dotfiles = git_config_bool(var, value);
+ return 0;
+ }
+
+ if (!strcmp(var, "core.unsetenvvars")) {
+ free(unset_environment_variables);
+ unset_environment_variables = xstrdup(value);
+ return 0;
+ }
+
+ return 0;
+}
+
+/* Normalizes NT paths as returned by some low-level APIs. */
+static wchar_t *normalize_ntpath(wchar_t *wbuf)
+{
+ int i;
+ /* fix absolute path prefixes */
+ if (wbuf[0] == '\\') {
+ /* strip NT namespace prefixes */
+ if (!wcsncmp(wbuf, L"\\??\\", 4) ||
+ !wcsncmp(wbuf, L"\\\\?\\", 4))
+ wbuf += 4;
+ else if (!wcsnicmp(wbuf, L"\\DosDevices\\", 12))
+ wbuf += 12;
+ /* replace remaining '...UNC\' with '\\' */
+ if (!wcsnicmp(wbuf, L"UNC\\", 4)) {
+ wbuf += 2;
+ *wbuf = '\\';
+ }
+ }
+ /* convert backslashes to slashes */
+ for (i = 0; wbuf[i]; i++)
+ if (wbuf[i] == '\\')
+ wbuf[i] = '/';
+ return wbuf;
+}
+
int mingw_unlink(const char *pathname)
{
int ret, tries = 0;
{
int ret;
wchar_t wpath[MAX_PATH];
+
+ if (!is_valid_win32_path(path)) {
+ errno = EINVAL;
+ return -1;
+ }
+
if (xutftowcs_path(wpath, path) < 0)
return -1;
ret = _wmkdir(wpath);
typedef int (*open_fn_t)(wchar_t const *wfilename, int oflags, ...);
va_list args;
unsigned mode;
- int fd;
+ int fd, create = (oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL);
wchar_t wfilename[MAX_PATH];
open_fn_t open_fn;
mode = va_arg(args, int);
va_end(args);
+ if (!is_valid_win32_path(filename)) {
+ errno = create ? EINVAL : ENOENT;
+ return -1;
+ }
+
if (filename && !strcmp(filename, "/dev/null"))
filename = "nul";
int hide = needs_hiding(filename);
FILE *file;
wchar_t wfilename[MAX_PATH], wotype[4];
+ if (!is_valid_win32_path(filename)) {
+ int create = otype && strchr(otype, 'w');
+ errno = create ? EINVAL : ENOENT;
+ return NULL;
+ }
if (filename && !strcmp(filename, "/dev/null"))
filename = "nul";
if (xutftowcs_path(wfilename, filename) < 0 ||
int hide = needs_hiding(filename);
FILE *file;
wchar_t wfilename[MAX_PATH], wotype[4];
+ if (!is_valid_win32_path(filename)) {
+ int create = otype && strchr(otype, 'w');
+ errno = create ? EINVAL : ENOENT;
+ return NULL;
+ }
if (filename && !strcmp(filename, "/dev/null"))
filename = "nul";
if (xutftowcs_path(wfilename, filename) < 0 ||
return winTime - 116444736000000000LL;
}
-static inline time_t filetime_to_time_t(const FILETIME *ft)
+static inline void filetime_to_timespec(const FILETIME *ft, struct timespec *ts)
{
- return (time_t)(filetime_to_hnsec(ft) / 10000000);
+ long long hnsec = filetime_to_hnsec(ft);
+ ts->tv_sec = (time_t)(hnsec / 10000000);
+ ts->tv_nsec = (hnsec % 10000000) * 100;
}
/**
buf->st_size = fdata.nFileSizeLow |
(((off_t)fdata.nFileSizeHigh)<<32);
buf->st_dev = buf->st_rdev = 0; /* not used by Git */
- buf->st_atime = filetime_to_time_t(&(fdata.ftLastAccessTime));
- buf->st_mtime = filetime_to_time_t(&(fdata.ftLastWriteTime));
- buf->st_ctime = filetime_to_time_t(&(fdata.ftCreationTime));
+ filetime_to_timespec(&(fdata.ftLastAccessTime), &(buf->st_atim));
+ filetime_to_timespec(&(fdata.ftLastWriteTime), &(buf->st_mtim));
+ filetime_to_timespec(&(fdata.ftCreationTime), &(buf->st_ctim));
if (fdata.dwFileAttributes & FILE_ATTRIBUTE_REPARSE_POINT) {
WIN32_FIND_DATAW findbuf;
HANDLE handle = FindFirstFileW(wfilename, &findbuf);
return do_lstat(follow, alt_name, buf);
}
+static int get_file_info_by_handle(HANDLE hnd, struct stat *buf)
+{
+ BY_HANDLE_FILE_INFORMATION fdata;
+
+ if (!GetFileInformationByHandle(hnd, &fdata)) {
+ errno = err_win_to_posix(GetLastError());
+ return -1;
+ }
+
+ buf->st_ino = 0;
+ buf->st_gid = 0;
+ buf->st_uid = 0;
+ buf->st_nlink = 1;
+ buf->st_mode = file_attr_to_st_mode(fdata.dwFileAttributes);
+ buf->st_size = fdata.nFileSizeLow |
+ (((off_t)fdata.nFileSizeHigh)<<32);
+ buf->st_dev = buf->st_rdev = 0; /* not used by Git */
+ filetime_to_timespec(&(fdata.ftLastAccessTime), &(buf->st_atim));
+ filetime_to_timespec(&(fdata.ftLastWriteTime), &(buf->st_mtim));
+ filetime_to_timespec(&(fdata.ftCreationTime), &(buf->st_ctim));
+ return 0;
+}
+
int mingw_lstat(const char *file_name, struct stat *buf)
{
return do_stat_internal(0, file_name, buf);
int mingw_fstat(int fd, struct stat *buf)
{
HANDLE fh = (HANDLE)_get_osfhandle(fd);
- BY_HANDLE_FILE_INFORMATION fdata;
+ DWORD avail, type = GetFileType(fh) & ~FILE_TYPE_REMOTE;
- if (fh == INVALID_HANDLE_VALUE) {
- errno = EBADF;
- return -1;
- }
- /* direct non-file handles to MS's fstat() */
- if (GetFileType(fh) != FILE_TYPE_DISK)
- return _fstati64(fd, buf);
+ switch (type) {
+ case FILE_TYPE_DISK:
+ return get_file_info_by_handle(fh, buf);
- if (GetFileInformationByHandle(fh, &fdata)) {
- buf->st_ino = 0;
- buf->st_gid = 0;
- buf->st_uid = 0;
+ case FILE_TYPE_CHAR:
+ case FILE_TYPE_PIPE:
+ /* initialize stat fields */
+ memset(buf, 0, sizeof(*buf));
buf->st_nlink = 1;
- buf->st_mode = file_attr_to_st_mode(fdata.dwFileAttributes);
- buf->st_size = fdata.nFileSizeLow |
- (((off_t)fdata.nFileSizeHigh)<<32);
- buf->st_dev = buf->st_rdev = 0; /* not used by Git */
- buf->st_atime = filetime_to_time_t(&(fdata.ftLastAccessTime));
- buf->st_mtime = filetime_to_time_t(&(fdata.ftLastWriteTime));
- buf->st_ctime = filetime_to_time_t(&(fdata.ftCreationTime));
+
+ if (type == FILE_TYPE_CHAR) {
+ buf->st_mode = _S_IFCHR;
+ } else {
+ buf->st_mode = _S_IFIFO;
+ if (PeekNamedPipe(fh, NULL, 0, NULL, &avail, NULL))
+ buf->st_size = avail;
+ }
return 0;
+
+ default:
+ errno = EBADF;
+ return -1;
}
- errno = EBADF;
- return -1;
}
static inline void time_t_to_filetime(time_t t, FILETIME *ft)
char *mingw_getcwd(char *pointer, int len)
{
- wchar_t wpointer[MAX_PATH];
- if (!_wgetcwd(wpointer, ARRAY_SIZE(wpointer)))
+ wchar_t cwd[MAX_PATH], wpointer[MAX_PATH];
+ DWORD ret = GetCurrentDirectoryW(ARRAY_SIZE(cwd), cwd);
+
+ if (!ret || ret >= ARRAY_SIZE(cwd)) {
+ errno = ret ? ENAMETOOLONG : err_win_to_posix(GetLastError());
+ return NULL;
+ }
+ ret = GetLongPathNameW(cwd, wpointer, ARRAY_SIZE(wpointer));
+ if (!ret && GetLastError() == ERROR_ACCESS_DENIED) {
+ HANDLE hnd = CreateFileW(cwd, 0,
+ FILE_SHARE_READ | FILE_SHARE_WRITE | FILE_SHARE_DELETE, NULL,
+ OPEN_EXISTING, FILE_FLAG_BACKUP_SEMANTICS, NULL);
+ if (hnd == INVALID_HANDLE_VALUE)
+ return NULL;
+ ret = GetFinalPathNameByHandleW(hnd, wpointer, ARRAY_SIZE(wpointer), 0);
+ CloseHandle(hnd);
+ if (!ret || ret >= ARRAY_SIZE(wpointer))
+ return NULL;
+ if (xwcstoutf(pointer, normalize_ntpath(wpointer), len) < 0)
+ return NULL;
+ return pointer;
+ }
+ if (!ret || ret >= ARRAY_SIZE(wpointer))
return NULL;
if (xwcstoutf(pointer, wpointer, len) < 0)
return NULL;
}
/*
- * See http://msdn2.microsoft.com/en-us/library/17w5ykft(vs.71).aspx
- * (Parsing C++ Command-Line Arguments)
+ * See "Parsing C++ Command-Line Arguments" at Microsoft's Docs:
+ * https://docs.microsoft.com/en-us/cpp/cpp/parsing-cpp-command-line-arguments
*/
static const char *quote_arg(const char *arg)
{
p++;
len++;
}
- if (*p == '"')
+ if (*p == '"' || !*p)
n += count*2 + 1;
continue;
}
count++;
*d++ = *arg++;
}
- if (*arg == '"') {
+ if (*arg == '"' || !*arg) {
while (count-- > 0)
*d++ = '\\';
+ /* don't escape the surrounding end quote */
+ if (!*arg)
+ break;
*d++ = '\\';
}
}
*d++ = *arg++;
}
*d++ = '"';
- *d++ = 0;
+ *d++ = '\0';
return q;
}
return prog;
}
-static int do_putenv(char **env, const char *name, int size, int free_old);
+static const wchar_t *wcschrnul(const wchar_t *s, wchar_t c)
+{
+ while (*s && *s != c)
+ s++;
+ return s;
+}
+
+/* Compare only keys */
+static int wenvcmp(const void *a, const void *b)
+{
+ wchar_t *p = *(wchar_t **)a, *q = *(wchar_t **)b;
+ size_t p_len, q_len;
+
+ /* Find the keys */
+ p_len = wcschrnul(p, L'=') - p;
+ q_len = wcschrnul(q, L'=') - q;
+
+ /* If the length differs, include the shorter key's NUL */
+ if (p_len < q_len)
+ p_len++;
+ else if (p_len > q_len)
+ p_len = q_len + 1;
-/* used number of elements of environ array, including terminating NULL */
-static int environ_size = 0;
-/* allocated size of environ array, in bytes */
-static int environ_alloc = 0;
+ return _wcsnicmp(p, q, p_len);
+}
+
+/* We need a stable sort to convert the environment between UTF-16 <-> UTF-8 */
+#ifndef INTERNAL_QSORT
+#include "qsort.c"
+#endif
/*
- * Create environment block suitable for CreateProcess. Merges current
- * process environment and the supplied environment changes.
+ * Build an environment block combining the inherited environment
+ * merged with the given list of settings.
+ *
+ * Values of the form "KEY=VALUE" in deltaenv override inherited values.
+ * Values of the form "KEY" in deltaenv delete inherited values.
+ *
+ * Multiple entries in deltaenv for the same key are explicitly allowed.
+ *
+ * We return a contiguous block of UNICODE strings with a final trailing
+ * zero word.
*/
static wchar_t *make_environment_block(char **deltaenv)
{
- wchar_t *wenvblk = NULL;
- char **tmpenv;
- int i = 0, size = environ_size, wenvsz = 0, wenvpos = 0;
+ wchar_t *wenv = GetEnvironmentStringsW(), *wdeltaenv, *result, *p;
+ size_t wlen, s, delta_size, size;
- while (deltaenv && deltaenv[i])
- i++;
+ wchar_t **array = NULL;
+ size_t alloc = 0, nr = 0, i;
- /* copy the environment, leaving space for changes */
- ALLOC_ARRAY(tmpenv, size + i);
- memcpy(tmpenv, environ, size * sizeof(char*));
+ size = 1; /* for extra NUL at the end */
- /* merge supplied environment changes into the temporary environment */
- for (i = 0; deltaenv && deltaenv[i]; i++)
- size = do_putenv(tmpenv, deltaenv[i], size, 0);
+ /* If there is no deltaenv to apply, simply return a copy. */
+ if (!deltaenv || !*deltaenv) {
+ for (p = wenv; p && *p; ) {
+ size_t s = wcslen(p) + 1;
+ size += s;
+ p += s;
+ }
- /* create environment block from temporary environment */
- for (i = 0; tmpenv[i]; i++) {
- size = 2 * strlen(tmpenv[i]) + 2; /* +2 for final \0 */
- ALLOC_GROW(wenvblk, (wenvpos + size) * sizeof(wchar_t), wenvsz);
- wenvpos += xutftowcs(&wenvblk[wenvpos], tmpenv[i], size) + 1;
+ ALLOC_ARRAY(result, size);
+ memcpy(result, wenv, size * sizeof(*wenv));
+ FreeEnvironmentStringsW(wenv);
+ return result;
+ }
+
+ /*
+ * If there is a deltaenv, let's accumulate all keys into `array`,
+ * sort them using the stable git_qsort() and then copy, skipping
+ * duplicate keys
+ */
+ for (p = wenv; p && *p; ) {
+ ALLOC_GROW(array, nr + 1, alloc);
+ s = wcslen(p) + 1;
+ array[nr++] = p;
+ p += s;
+ size += s;
+ }
+
+ /* (over-)assess size needed for wchar version of deltaenv */
+ for (delta_size = 0, i = 0; deltaenv[i]; i++)
+ delta_size += strlen(deltaenv[i]) * 2 + 1;
+ ALLOC_ARRAY(wdeltaenv, delta_size);
+
+ /* convert the deltaenv, appending to array */
+ for (i = 0, p = wdeltaenv; deltaenv[i]; i++) {
+ ALLOC_GROW(array, nr + 1, alloc);
+ wlen = xutftowcs(p, deltaenv[i], wdeltaenv + delta_size - p);
+ array[nr++] = p;
+ p += wlen + 1;
+ }
+
+ git_qsort(array, nr, sizeof(*array), wenvcmp);
+ ALLOC_ARRAY(result, size + delta_size);
+
+ for (p = result, i = 0; i < nr; i++) {
+ /* Skip any duplicate keys; last one wins */
+ while (i + 1 < nr && !wenvcmp(array + i, array + i + 1))
+ i++;
+
+ /* Skip "to delete" entry */
+ if (!wcschr(array[i], L'='))
+ continue;
+
+ size = wcslen(array[i]) + 1;
+ memcpy(p, array[i], size * sizeof(*p));
+ p += size;
+ }
+ *p = L'\0';
+
+ free(array);
+ free(wdeltaenv);
+ FreeEnvironmentStringsW(wenv);
+ return result;
+}
+
+static void do_unset_environment_variables(void)
+{
+ static int done;
+ char *p = unset_environment_variables;
+
+ if (done || !p)
+ return;
+ done = 1;
+
+ for (;;) {
+ char *comma = strchr(p, ',');
+
+ if (comma)
+ *comma = '\0';
+ unsetenv(p);
+ if (!comma)
+ break;
+ p = comma + 1;
}
- /* add final \0 terminator */
- wenvblk[wenvpos] = 0;
- free(tmpenv);
- return wenvblk;
}
struct pinfo_t {
wchar_t wcmd[MAX_PATH], wdir[MAX_PATH], *wargs, *wenvblk = NULL;
unsigned flags = CREATE_UNICODE_ENVIRONMENT;
BOOL ret;
+ HANDLE cons;
+
+ do_unset_environment_variables();
/* Determine whether or not we are associated to a console */
- HANDLE cons = CreateFile("CONOUT$", GENERIC_WRITE,
+ cons = CreateFile("CONOUT$", GENERIC_WRITE,
FILE_SHARE_WRITE, NULL, OPEN_EXISTING,
FILE_ATTRIBUTE_NORMAL, NULL);
if (cons == INVALID_HANDLE_VALUE) {
}
/*
- * Compare environment entries by key (i.e. stopping at '=' or '\0').
+ * UTF-8 versions of getenv(), putenv() and unsetenv().
+ * Internally, they use the CRT's stock UNICODE routines
+ * to avoid data loss.
*/
-static int compareenv(const void *v1, const void *v2)
+char *mingw_getenv(const char *name)
{
- const char *e1 = *(const char**)v1;
- const char *e2 = *(const char**)v2;
+#define GETENV_MAX_RETAIN 30
+ static char *values[GETENV_MAX_RETAIN];
+ static int value_counter;
+ int len_key, len_value;
+ wchar_t *w_key;
+ char *value;
+ wchar_t w_value[32768];
- for (;;) {
- int c1 = *e1++;
- int c2 = *e2++;
- c1 = (c1 == '=') ? 0 : tolower(c1);
- c2 = (c2 == '=') ? 0 : tolower(c2);
- if (c1 > c2)
- return 1;
- if (c1 < c2)
- return -1;
- if (c1 == 0)
- return 0;
- }
-}
+ if (!name || !*name)
+ return NULL;
-static int bsearchenv(char **env, const char *name, size_t size)
-{
- unsigned low = 0, high = size;
- while (low < high) {
- unsigned mid = low + ((high - low) >> 1);
- int cmp = compareenv(&env[mid], &name);
- if (cmp < 0)
- low = mid + 1;
- else if (cmp > 0)
- high = mid;
- else
- return mid;
+ len_key = strlen(name) + 1;
+ /* We cannot use xcalloc() here because that uses getenv() itself */
+ w_key = calloc(len_key, sizeof(wchar_t));
+ if (!w_key)
+ die("Out of memory, (tried to allocate %u wchar_t's)", len_key);
+ xutftowcs(w_key, name, len_key);
+ len_value = GetEnvironmentVariableW(w_key, w_value, ARRAY_SIZE(w_value));
+ if (!len_value && GetLastError() == ERROR_ENVVAR_NOT_FOUND) {
+ free(w_key);
+ return NULL;
}
- return ~low; /* not found, return 1's complement of insert position */
+ free(w_key);
+
+ len_value = len_value * 3 + 1;
+ /* We cannot use xcalloc() here because that uses getenv() itself */
+ value = calloc(len_value, sizeof(char));
+ if (!value)
+ die("Out of memory, (tried to allocate %u bytes)", len_value);
+ xwcstoutf(value, w_value, len_value);
+
+ /*
+ * We return `value` which is an allocated value and the caller is NOT
+ * expecting to have to free it, so we keep a round-robin array,
+ * invalidating the buffer after GETENV_MAX_RETAIN getenv() calls.
+ */
+ free(values[value_counter]);
+ values[value_counter++] = value;
+ if (value_counter >= ARRAY_SIZE(values))
+ value_counter = 0;
+
+ return value;
}
-/*
- * If name contains '=', then sets the variable, otherwise it unsets it
- * Size includes the terminating NULL. Env must have room for size + 1 entries
- * (in case of insert). Returns the new size. Optionally frees removed entries.
- */
-static int do_putenv(char **env, const char *name, int size, int free_old)
+int mingw_putenv(const char *namevalue)
{
- int i = bsearchenv(env, name, size - 1);
+ int size;
+ wchar_t *wide, *equal;
+ BOOL result;
- /* optionally free removed / replaced entry */
- if (i >= 0 && free_old)
- free(env[i]);
+ if (!namevalue || !*namevalue)
+ return 0;
- if (strchr(name, '=')) {
- /* if new value ('key=value') is specified, insert or replace entry */
- if (i < 0) {
- i = ~i;
- memmove(&env[i + 1], &env[i], (size - i) * sizeof(char*));
- size++;
- }
- env[i] = (char*) name;
- } else if (i >= 0) {
- /* otherwise ('key') remove existing entry */
- size--;
- memmove(&env[i], &env[i + 1], (size - i) * sizeof(char*));
+ size = strlen(namevalue) * 2 + 1;
+ wide = calloc(size, sizeof(wchar_t));
+ if (!wide)
+ die("Out of memory, (tried to allocate %u wchar_t's)", size);
+ xutftowcs(wide, namevalue, size);
+ equal = wcschr(wide, L'=');
+ if (!equal)
+ result = SetEnvironmentVariableW(wide, NULL);
+ else {
+ *equal = L'\0';
+ result = SetEnvironmentVariableW(wide, equal + 1);
}
- return size;
-}
+ free(wide);
-char *mingw_getenv(const char *name)
-{
- char *value;
- int pos = bsearchenv(environ, name, environ_size - 1);
- if (pos < 0)
- return NULL;
- value = strchr(environ[pos], '=');
- return value ? &value[1] : NULL;
-}
+ if (!result)
+ errno = err_win_to_posix(GetLastError());
-int mingw_putenv(const char *namevalue)
-{
- ALLOC_GROW(environ, (environ_size + 1) * sizeof(char*), environ_alloc);
- environ_size = do_putenv(environ, namevalue, environ_size, 1);
- return 0;
+ return result ? 0 : -1;
}
/*
WSAGetLastError());
for (name = libraries; *name; name++) {
- ipv6_dll = LoadLibrary(*name);
+ ipv6_dll = LoadLibraryExA(*name, NULL,
+ LOAD_LIBRARY_SEARCH_SYSTEM32);
if (!ipv6_dll)
continue;
return si.dwAllocationGranularity;
}
+/* See https://msdn.microsoft.com/en-us/library/windows/desktop/ms724435.aspx */
+enum EXTENDED_NAME_FORMAT {
+ NameDisplay = 3,
+ NameUserPrincipal = 8
+};
+
+static char *get_extended_user_info(enum EXTENDED_NAME_FORMAT type)
+{
+ DECLARE_PROC_ADDR(secur32.dll, BOOL, GetUserNameExW,
+ enum EXTENDED_NAME_FORMAT, LPCWSTR, PULONG);
+ static wchar_t wbuffer[1024];
+ DWORD len;
+
+ if (!INIT_PROC_ADDR(GetUserNameExW))
+ return NULL;
+
+ len = ARRAY_SIZE(wbuffer);
+ if (GetUserNameExW(type, wbuffer, &len)) {
+ char *converted = xmalloc((len *= 3));
+ if (xwcstoutf(converted, wbuffer, len) >= 0)
+ return converted;
+ free(converted);
+ }
+
+ return NULL;
+}
+
+char *mingw_query_user_email(void)
+{
+ return get_extended_user_info(NameUserPrincipal);
+}
+
struct passwd *getpwuid(int uid)
{
+ static unsigned initialized;
static char user_name[100];
- static struct passwd p;
+ static struct passwd *p;
+ DWORD len;
- DWORD len = sizeof(user_name);
- if (!GetUserName(user_name, &len))
+ if (initialized)
+ return p;
+
+ len = sizeof(user_name);
+ if (!GetUserName(user_name, &len)) {
+ initialized = 1;
return NULL;
- p.pw_name = user_name;
- p.pw_gecos = "unknown";
- p.pw_dir = NULL;
- return &p;
+ }
+
+ p = xmalloc(sizeof(*p));
+ p->pw_name = user_name;
+ p->pw_gecos = get_extended_user_info(NameDisplay);
+ if (!p->pw_gecos)
+ p->pw_gecos = "unknown";
+ p->pw_dir = NULL;
+
+ initialized = 1;
+ return p;
}
static HANDLE timer_event;
int link(const char *oldpath, const char *newpath)
{
- typedef BOOL (WINAPI *T)(LPCWSTR, LPCWSTR, LPSECURITY_ATTRIBUTES);
- static T create_hard_link = NULL;
wchar_t woldpath[MAX_PATH], wnewpath[MAX_PATH];
if (xutftowcs_path(woldpath, oldpath) < 0 ||
xutftowcs_path(wnewpath, newpath) < 0)
return -1;
- if (!create_hard_link) {
- create_hard_link = (T) GetProcAddress(
- GetModuleHandle("kernel32.dll"), "CreateHardLinkW");
- if (!create_hard_link)
- create_hard_link = (T)-1;
- }
- if (create_hard_link == (T)-1) {
- errno = ENOSYS;
- return -1;
- }
- if (!create_hard_link(wnewpath, woldpath, NULL)) {
+ if (!CreateHardLinkW(wnewpath, woldpath, NULL)) {
errno = err_win_to_posix(GetLastError());
return -1;
}
return -1;
}
+ int mingw_has_dos_drive_prefix(const char *path)
+ {
+ int i;
+
+ /*
+ * Does it start with an ASCII letter (i.e. highest bit not set),
+ * followed by a colon?
+ */
+ if (!(0x80 & (unsigned char)*path))
+ return *path && path[1] == ':' ? 2 : 0;
+
+ /*
+ * While drive letters must be letters of the English alphabet, it is
+ * possible to assign virtually _any_ Unicode character via `subst` as
+ * a drive letter to "virtual drives". Even `1`, or `ä`. Or fun stuff
+ * like this:
+ *
+ * subst ֍: %USERPROFILE%\Desktop
+ */
+ for (i = 1; i < 4 && (0x80 & (unsigned char)path[i]); i++)
+ ; /* skip first UTF-8 character */
+ return path[i] == ':' ? i + 1 : 0;
+ }
+
int mingw_skip_dos_drive_prefix(char **path)
{
int ret = has_dos_drive_prefix(*path);
setenv("TERM", "cygwin", 1);
}
+ int is_valid_win32_path(const char *path)
+ {
+ int preceding_space_or_period = 0, i = 0, periods = 0;
+
+ if (!protect_ntfs)
+ return 1;
+
+ skip_dos_drive_prefix((char **)&path);
+
+ for (;;) {
+ char c = *(path++);
+ switch (c) {
+ case '\0':
+ case '/': case '\\':
+ /* cannot end in ` ` or `.`, except for `.` and `..` */
+ if (preceding_space_or_period &&
+ (i != periods || periods > 2))
+ return 0;
+ if (!c)
+ return 1;
+
+ i = periods = preceding_space_or_period = 0;
+ continue;
+ case '.':
+ periods++;
+ /* fallthru */
+ case ' ':
+ preceding_space_or_period = 1;
+ i++;
+ continue;
+ case ':': /* DOS drive prefix was already skipped */
+ case '<': case '>': case '"': case '|': case '?': case '*':
+ /* illegal character */
+ return 0;
+ default:
+ if (c > '\0' && c < '\x20')
+ /* illegal character */
+ return 0;
+ }
+ preceding_space_or_period = 0;
+ i++;
+ }
+ }
+
/*
* Disable MSVCRT command line wildcard expansion (__getmainargs called from
* mingw startup code, see init.c in mingw runtime).
maxlen = wcslen(wargv[0]);
for (i = 1; i < argc; i++)
maxlen = max(maxlen, wcslen(wargv[i]));
- for (i = 0; wenv[i]; i++)
- maxlen = max(maxlen, wcslen(wenv[i]));
-
- /*
- * nedmalloc can't free CRT memory, allocate resizable environment
- * list. Note that xmalloc / xmemdupz etc. call getenv, so we cannot
- * use it while initializing the environment itself.
- */
- environ_size = i + 1;
- environ_alloc = alloc_nr(environ_size * sizeof(char*));
- environ = malloc_startup(environ_alloc);
/* allocate buffer (wchar_t encodes to max 3 UTF-8 bytes) */
maxlen = 3 * maxlen + 1;
/* convert command line arguments and environment to UTF-8 */
for (i = 0; i < argc; i++)
__argv[i] = wcstoutfdup_startup(buffer, wargv[i], maxlen);
- for (i = 0; wenv[i]; i++)
- environ[i] = wcstoutfdup_startup(buffer, wenv[i], maxlen);
- environ[i] = NULL;
free(buffer);
- /* sort environment for O(log n) getenv / putenv */
- qsort(environ, i, sizeof(char*), compareenv);
-
/* fix Windows specific environment settings */
setup_windows_environment();
+ unset_environment_variables = xstrdup("PERL5LIB");
+
/* initialize critical section for waitpid pinfo_t list */
InitializeCriticalSection(&pinfo_cs);
#undef _POSIX_THREAD_SAFE_FUNCTIONS
#endif
+extern int mingw_core_config(const char *var, const char *value, void *cb);
+#define platform_core_config mingw_core_config
+
/*
* things that are not available in header files
*/
char *mingw_getcwd(char *pointer, int len);
#define getcwd mingw_getcwd
+#ifdef NO_UNSETENV
+#error "NO_UNSETENV is incompatible with the Windows-specific startup code!"
+#endif
+
+/*
+ * We bind *env() routines (even the mingw_ ones) to private mingw_ versions.
+ * These talk to the CRT using UNICODE/wchar_t, but maintain the original
+ * narrow-char API.
+ *
+ * Note that the MSCRT maintains both ANSI (getenv()) and UNICODE (_wgetenv())
+ * routines and stores both versions of each environment variable in parallel
+ * (and secretly updates both when you set one or the other), but it uses CP_ACP
+ * to do the conversion rather than CP_UTF8.
+ *
+ * Since everything in the git code base is UTF8, we define the mingw_ routines
+ * to access the CRT using the UNICODE routines and manually convert them to
+ * UTF8. This also avoids round-trip problems.
+ *
+ * This also helps with our linkage, since "_wenviron" is publicly exported
+ * from the CRT. But to access "_environ" we would have to statically link
+ * to the CRT (/MT).
+ *
+ * We require NO_SETENV (and let gitsetenv() call our mingw_putenv).
+ */
+#define getenv mingw_getenv
+#define putenv mingw_putenv
+#define unsetenv mingw_putenv
char *mingw_getenv(const char *name);
-#define getenv mingw_getenv
-int mingw_putenv(const char *namevalue);
-#define putenv mingw_putenv
-#define unsetenv mingw_putenv
+int mingw_putenv(const char *name);
int mingw_gethostname(char *host, int namelen);
#define gethostname mingw_gethostname
}
/*
- * Use mingw specific stat()/lstat()/fstat() implementations on Windows.
+ * Use mingw specific stat()/lstat()/fstat() implementations on Windows,
+ * including our own struct stat with 64 bit st_size and nanosecond-precision
+ * file times.
*/
#ifndef __MINGW64_VERSION_MAJOR
#define off_t off64_t
#define lseek _lseeki64
+struct timespec {
+ time_t tv_sec;
+ long tv_nsec;
+};
#endif
-/* use struct stat with 64 bit st_size */
+struct mingw_stat {
+ _dev_t st_dev;
+ _ino_t st_ino;
+ _mode_t st_mode;
+ short st_nlink;
+ short st_uid;
+ short st_gid;
+ _dev_t st_rdev;
+ off64_t st_size;
+ struct timespec st_atim;
+ struct timespec st_mtim;
+ struct timespec st_ctim;
+};
+
+#define st_atime st_atim.tv_sec
+#define st_mtime st_mtim.tv_sec
+#define st_ctime st_ctim.tv_sec
+
#ifdef stat
#undef stat
#endif
-#define stat _stati64
+#define stat mingw_stat
int mingw_lstat(const char *file_name, struct stat *buf);
int mingw_stat(const char *file_name, struct stat *buf);
int mingw_fstat(int fd, struct stat *buf);
#endif
#define lstat mingw_lstat
-#ifndef _stati64
-# define _stati64(x,y) mingw_stat(x,y)
-#elif defined (_USE_32BIT_TIME_T)
-# define _stat32i64(x,y) mingw_stat(x,y)
-#else
-# define _stat64(x,y) mingw_stat(x,y)
-#endif
int mingw_utime(const char *file_name, const struct utimbuf *times);
#define utime mingw_utime
int winansi_isatty(int fd);
#define isatty winansi_isatty
+int winansi_dup2(int oldfd, int newfd);
+#define dup2 winansi_dup2
+
void winansi_init(void);
HANDLE winansi_get_osfhandle(int fd);
* git specific compatibility
*/
- #define has_dos_drive_prefix(path) \
- (isalpha(*(path)) && (path)[1] == ':' ? 2 : 0)
+ int mingw_has_dos_drive_prefix(const char *path);
+ #define has_dos_drive_prefix mingw_has_dos_drive_prefix
int mingw_skip_dos_drive_prefix(char **path);
#define skip_dos_drive_prefix mingw_skip_dos_drive_prefix
static inline int mingw_is_dir_sep(int c)
int mingw_offset_1st_component(const char *path);
#define offset_1st_component mingw_offset_1st_component
#define PATH_SEP ';'
+extern char *mingw_query_user_email(void);
+#define query_user_email mingw_query_user_email
#if !defined(__MINGW64_VERSION_MAJOR) && (!defined(_MSC_VER) || _MSC_VER < 1800)
#define PRIuMAX "I64u"
#define PRId64 "I64d"
#include <inttypes.h>
#endif
+ /**
+ * Verifies that the given path is a valid one on Windows.
+ *
+ * In particular, path segments are disallowed which
+ *
+ * - end in a period or a space (except the special directories `.` and `..`).
+ *
+ * - contain any of the reserved characters, e.g. `:`, `;`, `*`, etc
+ *
+ * Returns 1 upon success, otherwise 0.
+ */
+ int is_valid_win32_path(const char *path);
+ #define is_valid_path(path) is_valid_win32_path(path)
+
/**
* Converts UTF-8 encoded string to UTF-16LE.
*
RUNTIME_PREFIX = YesPlease
HAVE_WPGMPTR = YesWeDo
NO_ST_BLOCKS_IN_STRUCT_STAT = YesPlease
- NO_NSEC = YesPlease
USE_WIN32_MMAP = YesPlease
MMAP_PREVENTS_DELETE = UnfortunatelyYes
# USE_NED_ALLOCATOR = YesPlease
NO_PYTHON = YesPlease
BLK_SHA1 = YesPlease
ETAGS_TARGET = ETAGS
- NO_INET_PTON = YesPlease
- NO_INET_NTOP = YesPlease
NO_POSIX_GOODIES = UnfortunatelyYes
NATIVE_CRLF = YesPlease
DEFAULT_HELP_FORMAT = html
EXTLIBS = user32.lib advapi32.lib shell32.lib wininet.lib ws2_32.lib invalidcontinue.obj
PTHREAD_LIBS =
lib =
- BASIC_CFLAGS += -DPROTECT_NTFS_DEFAULT=1
ifndef DEBUG
BASIC_CFLAGS += -GL -Os -MD
BASIC_LDFLAGS += -LTCG
NO_NSEC = YesPlease
NEEDS_LIBGEN =
NEEDS_CRYPTO_WITH_SSL = YesPlease
- NEEDS_IDN_WITH_CURL = YesPlease
- NEEDS_SSL_WITH_CURL = YesPlease
NEEDS_RESOLV =
NO_HSTRERROR = YesPlease
NO_MMAP = YesPlease
# Missdetected, hence commented out, see below.
#NO_CURL = YesPlease
# Added manually, see above.
- NEEDS_SSL_WITH_CURL = YesPlease
HAVE_LIBCHARSET_H = YesPlease
HAVE_STRINGS_H = YesPlease
NEEDS_LIBICONV = YesPlease
RUNTIME_PREFIX = YesPlease
HAVE_WPGMPTR = YesWeDo
NO_ST_BLOCKS_IN_STRUCT_STAT = YesPlease
- NO_NSEC = YesPlease
USE_WIN32_MMAP = YesPlease
MMAP_PREVENTS_DELETE = UnfortunatelyYes
USE_NED_ALLOCATOR = YesPlease
NO_REGEX = YesPlease
NO_PYTHON = YesPlease
ETAGS_TARGET = ETAGS
- NO_INET_PTON = YesPlease
- NO_INET_NTOP = YesPlease
NO_POSIX_GOODIES = UnfortunatelyYes
DEFAULT_HELP_FORMAT = html
COMPAT_CFLAGS += -DNOGDI -Icompat -Icompat/win32
COMPAT_OBJS += compat/mingw.o compat/winansi.o \
compat/win32/pthread.o compat/win32/syslog.o \
compat/win32/dirent.o
- BASIC_CFLAGS += -DWIN32 -DPROTECT_NTFS_DEFAULT=1
+ BASIC_CFLAGS += -DWIN32
EXTLIBS += -lws2_32
GITLIBS += git.res
PTHREAD_LIBS =
return 0;
name++;
- return !oidcmp(&null_oid, &oid) && !strcmp(name, "capabilities^{}");
+ return oideq(&null_oid, &oid) && !strcmp(name, "capabilities^{}");
}
static void check_no_capabilities(const char *line, int len)
const char *colon = strchr(url, ':');
const char *slash = strchr(url, '/');
return !colon || (slash && slash < colon) ||
- has_dos_drive_prefix(url);
+ (has_dos_drive_prefix(url) && is_valid_path(url));
}
static const char *prot_name(enum protocol protocol)
int repository_format_precious_objects;
char *repository_format_partial_clone;
const char *core_partial_clone_filter_default;
+int repository_format_worktree_config;
const char *git_commit_encoding;
const char *git_log_output_encoding;
const char *apply_default_whitespace;
int merge_log_config = -1;
int precomposed_unicode = -1; /* see probe_utf8_pathname_composition() */
unsigned long pack_size_limit_cfg;
-enum hide_dotfiles_type hide_dotfiles = HIDE_DOTFILES_DOTGITONLY;
enum log_refs_config log_all_ref_updates = LOG_REFS_UNSET;
#ifndef PROTECT_HFS_DEFAULT
int protect_hfs = PROTECT_HFS_DEFAULT;
#ifndef PROTECT_NTFS_DEFAULT
- #define PROTECT_NTFS_DEFAULT 0
+ #define PROTECT_NTFS_DEFAULT 1
#endif
int protect_ntfs = PROTECT_NTFS_DEFAULT;
const char *core_fsmonitor;
#include "packfile.h"
#include "object-store.h"
#include "mem-pool.h"
+#include "commit-reach.h"
#define PACK_ID_BITS 16
#define MAX_PACK_ID ((1<<PACK_ID_BITS)-1)
static struct strbuf new_data = STRBUF_INIT;
static int seen_data_command;
static int require_explicit_termination;
+ static int allow_unsafe_features;
/* Signal handling */
static volatile sig_atomic_t checkpoint_requested;
unsigned int h = oid->hash[0] << 8 | oid->hash[1];
struct object_entry *e;
for (e = object_table[h]; e; e = e->next)
- if (!oidcmp(oid, &e->idx.oid))
+ if (oideq(oid, &e->idx.oid))
return e;
return NULL;
}
struct object_entry *e = object_table[h];
while (e) {
- if (!oidcmp(oid, &e->idx.oid))
+ if (oideq(oid, &e->idx.oid))
return e;
e = e->next;
}
duplicate_count_by_type[type]++;
return 1;
} else if (find_sha1_pack(oid.hash,
- get_packed_git(the_repository))) {
+ get_all_packs(the_repository))) {
e->type = type;
e->pack_id = MAX_PACK_ID;
e->idx.offset = 1; /* just not zero! */
truncate_pack(&checkpoint);
} else if (find_sha1_pack(oid.hash,
- get_packed_git(the_repository))) {
+ get_all_packs(the_repository))) {
e->type = OBJ_BLOB;
e->pack_id = MAX_PACK_ID;
e->idx.offset = 1; /* just not zero! */
if (!*slash1) {
if (!S_ISDIR(mode)
&& e->versions[1].mode == mode
- && !oidcmp(&e->versions[1].oid, oid))
+ && oideq(&e->versions[1].oid, oid))
return 0;
e->versions[1].mode = mode;
oidcpy(&e->versions[1].oid, oid);
if (!export_marks_file || (import_marks_file && !import_marks_file_done))
return;
+ if (safe_create_leading_directories_const(export_marks_file)) {
+ failure |= error_errno("unable to create leading directories of %s",
+ export_marks_file);
+ return;
+ }
+
if (hold_lock_file_for_update(&mark_lock, export_marks_file, 0) < 0) {
failure |= error_errno("Unable to write marks file %s",
export_marks_file);
struct object_entry *oe = find_mark(idnum);
if (oe->type != OBJ_COMMIT)
die("Mark :%" PRIuMAX " not a commit", idnum);
- if (oidcmp(&b->oid, &oe->idx.oid)) {
+ if (!oideq(&b->oid, &oe->idx.oid)) {
oidcpy(&b->oid, &oe->idx.oid);
if (oe->pack_id != MAX_PACK_ID) {
unsigned long size;
else
die("Invalid ref name or SHA1 expression: %s", from);
- if (b->branch_tree.tree && oidcmp(&oid, &b->branch_tree.versions[1].oid)) {
+ if (b->branch_tree.tree && !oideq(&oid, &b->branch_tree.versions[1].oid)) {
release_tree_content_recursive(b->branch_tree.tree);
b->branch_tree.tree = NULL;
}
die("Object %s is a %s but a blob was expected.",
oid_to_hex(oid), type_name(type));
strbuf_reset(&line);
- strbuf_addf(&line, "%s %s %lu\n", oid_to_hex(oid),
- type_name(type), size);
+ strbuf_addf(&line, "%s %s %"PRIuMAX"\n", oid_to_hex(oid),
+ type_name(type), (uintmax_t)size);
cat_blob_write(line.buf, line.len);
strbuf_release(&line);
cat_blob_write(buf, size);
}
import_marks_file = make_fast_import_path(marks);
- safe_create_leading_directories_const(import_marks_file);
import_marks_file_from_stream = from_stream;
import_marks_file_ignore_missing = ignore_missing;
}
static void option_export_marks(const char *marks)
{
export_marks_file = make_fast_import_path(marks);
- safe_create_leading_directories_const(export_marks_file);
}
static void option_cat_blob_fd(const char *fd)
option_active_branches(option);
} else if (skip_prefix(option, "export-pack-edges=", &option)) {
option_export_pack_edges(option);
- } else if (starts_with(option, "quiet")) {
+ } else if (!strcmp(option, "quiet")) {
show_stats = 0;
- } else if (starts_with(option, "stats")) {
+ } else if (!strcmp(option, "stats")) {
show_stats = 1;
+ } else if (!strcmp(option, "allow-unsafe-features")) {
+ ; /* already handled during early option parsing */
} else {
return 0;
}
return 1;
}
+ static void check_unsafe_feature(const char *feature, int from_stream)
+ {
+ if (from_stream && !allow_unsafe_features)
+ die(_("feature '%s' forbidden in input without --allow-unsafe-features"),
+ feature);
+ }
+
static int parse_one_feature(const char *feature, int from_stream)
{
const char *arg;
if (skip_prefix(feature, "date-format=", &arg)) {
option_date_format(arg);
} else if (skip_prefix(feature, "import-marks=", &arg)) {
+ check_unsafe_feature("import-marks", from_stream);
option_import_marks(arg, from_stream, 0);
} else if (skip_prefix(feature, "import-marks-if-exists=", &arg)) {
+ check_unsafe_feature("import-marks-if-exists", from_stream);
option_import_marks(arg, from_stream, 1);
} else if (skip_prefix(feature, "export-marks=", &arg)) {
+ check_unsafe_feature(feature, from_stream);
option_export_marks(arg);
} else if (!strcmp(feature, "get-mark")) {
; /* Don't die - this feature is supported */
avail_tree_table = xcalloc(avail_tree_table_sz, sizeof(struct avail_tree_content*));
marks = mem_pool_calloc(&fi_mem_pool, 1, sizeof(struct mark_set));
+ /*
+ * We don't parse most options until after we've seen the set of
+ * "feature" lines at the start of the stream (which allows the command
+ * line to override stream data). But we must do an early parse of any
+ * command-line options that impact how we interpret the feature lines.
+ */
+ for (i = 1; i < argc; i++) {
+ const char *arg = argv[i];
+ if (*arg != '-' || !strcmp(arg, "--"))
+ break;
+ if (!strcmp(arg, "--allow-unsafe-features"))
+ allow_unsafe_features = 1;
+ }
+
global_argc = argc;
global_argv = argv;
#include "fsck.h"
#include "refs.h"
#include "utf8.h"
-#include "sha1-array.h"
#include "decorate.h"
#include "oidset.h"
#include "packfile.h"
FUNC(GITMODULES_SYMLINK, ERROR) \
FUNC(GITMODULES_URL, ERROR) \
FUNC(GITMODULES_PATH, ERROR) \
+ FUNC(GITMODULES_UPDATE, ERROR) \
/* warnings */ \
FUNC(BAD_FILEMODE, WARN) \
FUNC(EMPTY_NAME, WARN) \
static void init_skiplist(struct fsck_options *options, const char *path)
{
- static struct oid_array skiplist = OID_ARRAY_INIT;
- int sorted, fd;
- char buffer[GIT_MAX_HEXSZ + 1];
+ FILE *fp;
+ struct strbuf sb = STRBUF_INIT;
struct object_id oid;
- if (options->skiplist)
- sorted = options->skiplist->sorted;
- else {
- sorted = 1;
- options->skiplist = &skiplist;
- }
-
- fd = open(path, O_RDONLY);
- if (fd < 0)
+ fp = fopen(path, "r");
+ if (!fp)
die("Could not open skip list: %s", path);
- for (;;) {
+ while (!strbuf_getline(&sb, fp)) {
const char *p;
- int result = read_in_full(fd, buffer, sizeof(buffer));
- if (result < 0)
- die_errno("Could not read '%s'", path);
- if (!result)
- break;
- if (parse_oid_hex(buffer, &oid, &p) || *p != '\n')
- die("Invalid SHA-1: %s", buffer);
- oid_array_append(&skiplist, &oid);
- if (sorted && skiplist.nr > 1 &&
- oidcmp(&skiplist.oid[skiplist.nr - 2],
- &oid) > 0)
- sorted = 0;
- }
- close(fd);
+ const char *hash;
+
+ /*
+ * Allow trailing comments, leading whitespace
+ * (including before commits), and empty or whitespace
+ * only lines.
+ */
+ hash = strchr(sb.buf, '#');
+ if (hash)
+ strbuf_setlen(&sb, hash - sb.buf);
+ strbuf_trim(&sb);
+ if (!sb.len)
+ continue;
- if (sorted)
- skiplist.sorted = 1;
+ if (parse_oid_hex(sb.buf, &oid, &p) || *p != '\0')
+ die("Invalid SHA-1: %s", sb.buf);
+ oidset_insert(&options->skiplist, &oid);
+ }
+ if (ferror(fp))
+ die_errno("Could not read '%s'", path);
+ fclose(fp);
+ strbuf_release(&sb);
}
static int parse_msg_type(const char *str)
static int object_on_skiplist(struct fsck_options *opts, struct object *obj)
{
- if (opts && opts->skiplist && obj)
- return oid_array_lookup(opts->skiplist, &obj->oid) >= 0;
- return 0;
+ return opts && obj && oidset_contains(&opts->skiplist, &obj->oid);
}
__attribute__((format (printf, 4, 5)))
while (desc.size) {
unsigned mode;
- const char *name;
+ const char *name, *backslash;
const struct object_id *oid;
oid = tree_entry_extract(&desc, &name, &mode);
".gitmodules is a symbolic link");
}
+ if ((backslash = strchr(name, '\\'))) {
+ while (backslash) {
+ backslash++;
+ has_dotgit |= is_ntfs_dotgit(backslash);
+ if (is_ntfs_dotgitmodules(backslash)) {
+ if (!S_ISLNK(mode))
+ oidset_insert(&gitmodules_found, oid);
+ else
+ retval += report(options, &item->object,
+ FSCK_MSG_GITMODULES_SYMLINK,
+ ".gitmodules is a symbolic link");
+ }
+ backslash = strchr(backslash, '\\');
+ }
+ }
+
if (update_tree_entry_gently(&desc)) {
retval += report(options, &item->object, FSCK_MSG_BAD_TREE, "cannot be parsed as a tree");
break;
FSCK_MSG_GITMODULES_PATH,
"disallowed submodule path: %s",
value);
+ if (!strcmp(key, "update") && value &&
+ parse_submodule_update_type(value) == SM_UPDATE_COMMAND)
+ data->ret |= report(data->options, data->obj,
+ FSCK_MSG_GITMODULES_UPDATE,
+ "disallowed submodule update setting: %s",
+ value);
free(name);
return 0;
#define _SGI_SOURCE 1
#if defined(WIN32) && !defined(__CYGWIN__) /* Both MinGW and MSVC */
-# if defined (_MSC_VER) && !defined(_WIN32_WINNT)
-# define _WIN32_WINNT 0x0502
+# if !defined(_WIN32_WINNT)
+# define _WIN32_WINNT 0x0600
# endif
#define WIN32_LEAN_AND_MEAN /* stops windows.h including winsock.h */
#include <winsock2.h>
#include <regex.h>
#include <utime.h>
#include <syslog.h>
-#ifndef NO_SYS_POLL_H
+#if !defined(NO_POLL_H)
+#include <poll.h>
+#elif !defined(NO_SYS_POLL_H)
#include <sys/poll.h>
#else
+/* Pull the compat stuff */
#include <poll.h>
#endif
#ifdef HAVE_BSD_SYSCTL
#define _PATH_DEFPATH "/usr/local/bin:/usr/bin:/bin"
#endif
+#ifndef platform_core_config
+static inline int noop_core_config(const char *var, const char *value, void *cb)
+{
+ return 0;
+}
+#define platform_core_config noop_core_config
+#endif
+
#ifndef has_dos_drive_prefix
static inline int git_has_dos_drive_prefix(const char *path)
{
#define offset_1st_component git_offset_1st_component
#endif
+ #ifndef is_valid_path
+ #define is_valid_path(path) 1
+ #endif
+
#ifndef find_last_dir_sep
static inline char *git_find_last_dir_sep(const char *path)
{
#define find_last_dir_sep git_find_last_dir_sep
#endif
+#ifndef query_user_email
+#define query_user_email() NULL
+#endif
+
#if defined(__HP_cc) && (__HP_cc >= 61000)
#define NORETURN __attribute__((noreturn))
#define NORETURN_PTR
#define LAST_ARG_MUST_BE_NULL
#endif
+#define MAYBE_UNUSED __attribute__((__unused__))
+
#include "compat/bswap.h"
#include "wildmatch.h"
#define FREE_AND_NULL(p) do { free(p); (p) = NULL; } while (0)
#define ALLOC_ARRAY(x, alloc) (x) = xmalloc(st_mult(sizeof(*(x)), (alloc)))
+#define CALLOC_ARRAY(x, alloc) (x) = xcalloc((alloc), sizeof(*(x)));
#define REALLOC_ARRAY(x, alloc) (x) = xrealloc((x), st_mult(sizeof(*(x)), (alloc)))
#define COPY_ARRAY(dst, src, n) copy_array((dst), (src), (n), sizeof(*(dst)) + \
cached=
recursive=
init=
+ require_init=
files=
remote=
nofetch=
value=$(git config submodule."$name"."$option")
if test -z "$value"
then
- value=$(git config -f .gitmodules submodule."$name"."$option")
+ value=$(git submodule--helper config submodule."$name"."$option")
fi
printf '%s' "${value:-$default}"
}
n=$(($1 + 0)) 2>/dev/null && test "$n" = "$1"
}
+# Given a full hex object ID, is this the zero OID?
+is_zero_oid () {
+ echo "$1" | sane_egrep '^0+$' >/dev/null 2>&1
+}
+
# Sanitize the local git environment for use within a submodule. We
# can't simply use clear_local_git_env since we want to preserve some
# of the settings from GIT_CONFIG_PARAMETERS.
shift
done
+ if ! git submodule--helper config --check-writeable >/dev/null 2>&1
+ then
+ die "$(eval_gettext "please make sure that the .gitmodules file is in the working tree")"
+ fi
+
if test -n "$reference_path"
then
is_absolute_path "$reference_path" ||
git add --no-warn-embedded-repo $force "$sm_path" ||
die "$(eval_gettext "Failed to add submodule '\$sm_path'")"
- git config -f .gitmodules submodule."$sm_name".path "$sm_path" &&
- git config -f .gitmodules submodule."$sm_name".url "$repo" &&
+ git submodule--helper config submodule."$sm_name".path "$sm_path" &&
+ git submodule--helper config submodule."$sm_name".url "$repo" &&
if test -n "$branch"
then
- git config -f .gitmodules submodule."$sm_name".branch "$branch"
+ git submodule--helper config submodule."$sm_name".branch "$branch"
fi &&
git add --force .gitmodules ||
die "$(eval_gettext "Failed to register submodule '\$sm_path'")"
-i|--init)
init=1
;;
+ --require-init)
+ init=1
+ require_init=1
+ ;;
--remote)
remote=1
;;
${reference:+"$reference"} \
${dissociate:+"--dissociate"} \
${depth:+--depth "$depth"} \
+ ${require_init:+--require-init} \
$recommend_shallow \
$jobs \
"$@" || echo "#unmatched" $?
} | {
err=
- while read -r mode sha1 stage just_cloned sm_path
+ while read -r quickabort sha1 just_cloned sm_path
do
- die_if_unmatched "$mode" "$sha1"
+ die_if_unmatched "$quickabort" "$sha1"
- name=$(git submodule--helper name "$sm_path") || exit
- if ! test -z "$update"
- then
- update_module=$update
- else
- update_module=$(git config submodule."$name".update)
- if test -z "$update_module"
- then
- update_module="checkout"
- fi
- fi
+ git submodule--helper ensure-core-worktree "$sm_path"
+
+ update_module=$(git submodule--helper update-module-mode $just_cloned "$sm_path" $update)
displaypath=$(git submodule--helper relative-path "$prefix$sm_path" "$wt_prefix")
if test $just_cloned -eq 1
then
subsha1=
- case "$update_module" in
- merge | rebase | none)
- update_module=checkout ;;
- esac
else
subsha1=$(sanitize_submodule_env; cd "$sm_path" &&
git rev-parse --verify HEAD) ||
must_die_on_failure=yes
;;
*)
- die "$(eval_gettext "Invalid update mode '$update_module' for submodule '$name'")"
+ die "$(eval_gettext "Invalid update mode '$update_module' for submodule path '$path'")"
esac
if (sanitize_submodule_env; cd "$sm_path" && $command "$sha1")
while read -r mod_src mod_dst sha1_src sha1_dst status name
do
if test -z "$cached" &&
- test $sha1_dst = 0000000000000000000000000000000000000000
+ is_zero_oid $sha1_dst
then
case "$mod_dst" in
160000)
static struct common_dir common_list[] = {
{ 0, 1, 0, "branches" },
+ { 0, 1, 0, "common" },
{ 0, 1, 0, "hooks" },
{ 0, 1, 0, "info" },
{ 0, 0, 1, "info/sparse-checkout" },
{ 0, 1, 0, "objects" },
{ 0, 1, 0, "refs" },
{ 0, 1, 1, "refs/bisect" },
+ { 0, 1, 1, "refs/worktree" },
{ 0, 1, 0, "remotes" },
{ 0, 1, 0, "worktrees" },
{ 0, 1, 0, "rr-cache" },
}
}
- static int only_spaces_and_periods(const char *path, size_t len, size_t skip)
+ /*
+ * On NTFS, we need to be careful to disallow certain synonyms of the `.git/`
+ * directory:
+ *
+ * - For historical reasons, file names that end in spaces or periods are
+ * automatically trimmed. Therefore, `.git . . ./` is a valid way to refer
+ * to `.git/`.
+ *
+ * - For other historical reasons, file names that do not conform to the 8.3
+ * format (up to eight characters for the basename, three for the file
+ * extension, certain characters not allowed such as `+`, etc) are associated
+ * with a so-called "short name", at least on the `C:` drive by default.
+ * Which means that `git~1/` is a valid way to refer to `.git/`.
+ *
+ * Note: Technically, `.git/` could receive the short name `git~2` if the
+ * short name `git~1` were already used. In Git, however, we guarantee that
+ * `.git` is the first item in a directory, therefore it will be associated
+ * with the short name `git~1` (unless short names are disabled).
+ *
+ * - For yet other historical reasons, NTFS supports so-called "Alternate Data
+ * Streams", i.e. metadata associated with a given file, referred to via
+ * `<filename>:<stream-name>:<stream-type>`. There exists a default stream
+ * type for directories, allowing `.git/` to be accessed via
+ * `.git::$INDEX_ALLOCATION/`.
+ *
+ * When this function returns 1, it indicates that the specified file/directory
+ * name refers to a `.git` file or directory, or to any of these synonyms, and
+ * Git should therefore not track it.
+ *
+ * For performance reasons, _all_ Alternate Data Streams of `.git/` are
+ * forbidden, not just `::$INDEX_ALLOCATION`.
+ *
+ * This function is intended to be used by `git fsck` even on platforms where
+ * the backslash is a regular filename character, therefore it needs to handle
+ * backlash characters in the provided `name` specially: they are interpreted
+ * as directory separators.
+ */
+ int is_ntfs_dotgit(const char *name)
{
- if (len < skip)
+ char c;
+
+ /*
+ * Note that when we don't find `.git` or `git~1` we end up with `name`
+ * advanced partway through the string. That's okay, though, as we
+ * return immediately in those cases, without looking at `name` any
+ * further.
+ */
+ c = *(name++);
+ if (c == '.') {
+ /* .git */
+ if (((c = *(name++)) != 'g' && c != 'G') ||
+ ((c = *(name++)) != 'i' && c != 'I') ||
+ ((c = *(name++)) != 't' && c != 'T'))
+ return 0;
+ } else if (c == 'g' || c == 'G') {
+ /* git ~1 */
+ if (((c = *(name++)) != 'i' && c != 'I') ||
+ ((c = *(name++)) != 't' && c != 'T') ||
+ *(name++) != '~' ||
+ *(name++) != '1')
+ return 0;
+ } else
return 0;
- len -= skip;
- path += skip;
- while (len-- > 0) {
- char c = *(path++);
- if (c != ' ' && c != '.')
+
+ for (;;) {
+ c = *(name++);
+ if (!c || c == '\\' || c == '/' || c == ':')
+ return 1;
+ if (c != '.' && c != ' ')
return 0;
}
- return 1;
- }
-
- int is_ntfs_dotgit(const char *name)
- {
- size_t len;
-
- for (len = 0; ; len++)
- if (!name[len] || name[len] == '\\' || is_dir_sep(name[len])) {
- if (only_spaces_and_periods(name, len, 4) &&
- !strncasecmp(name, ".git", 4))
- return 1;
- if (only_spaces_and_periods(name, len, 5) &&
- !strncasecmp(name, "git~1", 5))
- return 1;
- if (name[len] != '\\')
- return 0;
- name += len + 1;
- len = -1;
- }
}
static int is_ntfs_dot_generic(const char *name,
only_spaces_and_periods:
for (;;) {
char c = name[i++];
- if (!c)
+ if (!c || c == ':')
return 1;
if (c != ' ' && c != '.')
return 0;
#include "split-index.h"
#include "utf8.h"
#include "fsmonitor.h"
+#include "thread-utils.h"
+#include "progress.h"
/* Mask for the name length in ce_flags in the on-disk index */
#define CACHE_EXT_LINK 0x6c696e6b /* "link" */
#define CACHE_EXT_UNTRACKED 0x554E5452 /* "UNTR" */
#define CACHE_EXT_FSMONITOR 0x46534D4E /* "FSMN" */
+#define CACHE_EXT_ENDOFINDEXENTRIES 0x454F4945 /* "EOIE" */
+#define CACHE_EXT_INDEXENTRYOFFSETTABLE 0x49454F54 /* "IEOT" */
/* changes that can be kept in $GIT_DIR/index (basically all extensions) */
#define EXTMASK (RESOLVE_UNDO_CHANGED | CACHE_TREE_CHANGED | \
}
}
-static int ce_compare_data(const struct cache_entry *ce, struct stat *st)
+static int ce_compare_data(struct index_state *istate,
+ const struct cache_entry *ce,
+ struct stat *st)
{
int match = -1;
int fd = git_open_cloexec(ce->name, O_RDONLY);
if (fd >= 0) {
struct object_id oid;
- if (!index_fd(&oid, fd, st, OBJ_BLOB, ce->name, 0))
- match = oidcmp(&oid, &ce->oid);
+ if (!index_fd(istate, &oid, fd, st, OBJ_BLOB, ce->name, 0))
+ match = !oideq(&oid, &ce->oid);
/* index_fd() closed the file descriptor already */
}
return match;
*/
if (resolve_gitlink_ref(ce->name, "HEAD", &oid) < 0)
return 0;
- return oidcmp(&oid, &ce->oid);
+ return !oideq(&oid, &ce->oid);
}
-static int ce_modified_check_fs(const struct cache_entry *ce, struct stat *st)
+static int ce_modified_check_fs(struct index_state *istate,
+ const struct cache_entry *ce,
+ struct stat *st)
{
switch (st->st_mode & S_IFMT) {
case S_IFREG:
- if (ce_compare_data(ce, st))
+ if (ce_compare_data(istate, ce, st))
return DATA_CHANGED;
break;
case S_IFLNK:
if (assume_racy_is_modified)
changed |= DATA_CHANGED;
else
- changed |= ce_modified_check_fs(ce, st);
+ changed |= ce_modified_check_fs(istate, ce, st);
}
return changed;
(S_ISGITLINK(ce->ce_mode) || ce->ce_stat_data.sd_size != 0))
return changed;
- changed_fs = ce_modified_check_fs(ce, st);
+ changed_fs = ce_modified_check_fs(istate, ce, st);
if (changed_fs)
return changed | changed_fs;
return 0;
}
}
if (!intent_only) {
- if (index_path(&ce->oid, path, st, newflags)) {
+ if (index_path(istate, &ce->oid, path, st, newflags)) {
discard_cache_entry(ce);
return error("unable to index file %s", path);
}
/* It was suspected to be racily clean, but it turns out to be Ok */
was_same = (alias &&
!ce_stage(alias) &&
- !oidcmp(&alias->oid, &ce->oid) &&
+ oideq(&alias->oid, &ce->oid) &&
ce->ce_mode == alias->ce_mode);
if (pretend)
ce->ce_namelen = len;
ce->ce_mode = create_ce_mode(mode);
- ret = refresh_cache_entry(&the_index, ce, refresh_options);
+ ret = refresh_cache_entry(istate, ce, refresh_options);
if (ret != ce)
discard_cache_entry(ce);
return ret;
if (has_dos_drive_prefix(path))
return 0;
+ if (!is_valid_path(path))
+ return 0;
+
goto inside;
for (;;) {
if (!c)
if ((c == '.' && !verify_dotfile(path, mode)) ||
is_dir_sep(c) || c == '\0')
return 0;
+ } else if (c == '\\' && protect_ntfs) {
+ if (is_ntfs_dotgit(path))
+ return 0;
+ if (S_ISLNK(mode)) {
+ if (is_ntfs_dotgitmodules(path))
+ return 0;
+ }
}
+
c = *path++;
}
}
const char *typechange_fmt;
const char *added_fmt;
const char *unmerged_fmt;
- uint64_t start = getnanotime();
+ struct progress *progress = NULL;
+
+ if (flags & REFRESH_PROGRESS && isatty(2))
+ progress = start_delayed_progress(_("Refresh index"),
+ istate->cache_nr);
+ trace_performance_enter();
modified_fmt = (in_porcelain ? "M\t%s\n" : "%s: needs update\n");
deleted_fmt = (in_porcelain ? "D\t%s\n" : "%s: needs update\n");
typechange_fmt = (in_porcelain ? "T\t%s\n" : "%s needs update\n");
added_fmt = (in_porcelain ? "A\t%s\n" : "%s needs update\n");
unmerged_fmt = (in_porcelain ? "U\t%s\n" : "%s: needs merge\n");
+ /*
+ * Use the multi-threaded preload_index() to refresh most of the
+ * cache entries quickly then in the single threaded loop below,
+ * we only have to do the special cases that are left.
+ */
+ preload_index(istate, pathspec, 0);
for (i = 0; i < istate->cache_nr; i++) {
struct cache_entry *ce, *new_entry;
int cache_errno = 0;
if (ignore_submodules && S_ISGITLINK(ce->ce_mode))
continue;
- if (pathspec && !ce_path_match(&the_index, ce, pathspec, seen))
+ if (pathspec && !ce_path_match(istate, ce, pathspec, seen))
filtered = 1;
if (ce_stage(ce)) {
new_entry = refresh_cache_ent(istate, ce, options, &cache_errno, &changed);
if (new_entry == ce)
continue;
+ if (progress)
+ display_progress(progress, i);
if (!new_entry) {
const char *fmt;
replace_index_entry(istate, i, new_entry);
}
- trace_performance_since(start, "refresh index");
+ if (progress) {
+ display_progress(progress, istate->cache_nr);
+ stop_progress(&progress);
+ }
+ trace_performance_leave("refresh index");
return has_errors;
}
/* Allow fsck to force verification of the cache entry order. */
int verify_ce_order;
-static int verify_hdr(struct cache_header *hdr, unsigned long size)
+static int verify_hdr(const struct cache_header *hdr, unsigned long size)
{
git_hash_ctx c;
unsigned char hash[GIT_MAX_RAWSZ];
the_hash_algo->init_fn(&c);
the_hash_algo->update_fn(&c, hdr, size - the_hash_algo->rawsz);
the_hash_algo->final_fn(hash, &c);
- if (hashcmp(hash, (unsigned char *)hdr + size - the_hash_algo->rawsz))
+ if (!hasheq(hash, (unsigned char *)hdr + size - the_hash_algo->rawsz))
return error("bad index file sha1 signature");
return 0;
}
static int read_index_extension(struct index_state *istate,
- const char *ext, void *data, unsigned long sz)
+ const char *ext, const char *data, unsigned long sz)
{
switch (CACHE_EXT(ext)) {
case CACHE_EXT_TREE:
case CACHE_EXT_FSMONITOR:
read_fsmonitor_extension(istate, data, sz);
break;
+ case CACHE_EXT_ENDOFINDEXENTRIES:
+ case CACHE_EXT_INDEXENTRYOFFSETTABLE:
+ /* already handled in do_read_index() */
+ break;
default:
if (*ext < 'A' || 'Z' < *ext)
return error("index uses %.4s extension, which we do not understand",
return read_index_from(istate, get_index_file(), get_git_dir());
}
-static struct cache_entry *cache_entry_from_ondisk(struct mem_pool *mem_pool,
- struct ondisk_cache_entry *ondisk,
- unsigned int flags,
- const char *name,
- size_t len)
-{
- struct cache_entry *ce = mem_pool__ce_alloc(mem_pool, len);
-
- ce->ce_stat_data.sd_ctime.sec = get_be32(&ondisk->ctime.sec);
- ce->ce_stat_data.sd_mtime.sec = get_be32(&ondisk->mtime.sec);
- ce->ce_stat_data.sd_ctime.nsec = get_be32(&ondisk->ctime.nsec);
- ce->ce_stat_data.sd_mtime.nsec = get_be32(&ondisk->mtime.nsec);
- ce->ce_stat_data.sd_dev = get_be32(&ondisk->dev);
- ce->ce_stat_data.sd_ino = get_be32(&ondisk->ino);
- ce->ce_mode = get_be32(&ondisk->mode);
- ce->ce_stat_data.sd_uid = get_be32(&ondisk->uid);
- ce->ce_stat_data.sd_gid = get_be32(&ondisk->gid);
- ce->ce_stat_data.sd_size = get_be32(&ondisk->size);
- ce->ce_flags = flags & ~CE_NAMEMASK;
- ce->ce_namelen = len;
- ce->index = 0;
- hashcpy(ce->oid.hash, ondisk->sha1);
- memcpy(ce->name, name, len);
- ce->name[len] = '\0';
- return ce;
-}
-
-/*
- * Adjacent cache entries tend to share the leading paths, so it makes
- * sense to only store the differences in later entries. In the v4
- * on-disk format of the index, each on-disk cache entry stores the
- * number of bytes to be stripped from the end of the previous name,
- * and the bytes to append to the result, to come up with its name.
- */
-static unsigned long expand_name_field(struct strbuf *name, const char *cp_)
-{
- const unsigned char *ep, *cp = (const unsigned char *)cp_;
- size_t len = decode_varint(&cp);
-
- if (name->len < len)
- die("malformed name field in the index");
- strbuf_remove(name, name->len - len, len);
- for (ep = cp; *ep; ep++)
- ; /* find the end */
- strbuf_add(name, cp, ep - cp);
- return (const char *)ep + 1 - cp_;
-}
-
-static struct cache_entry *create_from_disk(struct mem_pool *mem_pool,
+static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
+ unsigned int version,
struct ondisk_cache_entry *ondisk,
unsigned long *ent_size,
- struct strbuf *previous_name)
+ const struct cache_entry *previous_ce)
{
struct cache_entry *ce;
size_t len;
const char *name;
unsigned int flags;
+ size_t copy_len = 0;
+ /*
+ * Adjacent cache entries tend to share the leading paths, so it makes
+ * sense to only store the differences in later entries. In the v4
+ * on-disk format of the index, each on-disk cache entry stores the
+ * number of bytes to be stripped from the end of the previous name,
+ * and the bytes to append to the result, to come up with its name.
+ */
+ int expand_name_field = version == 4;
/* On-disk flags are just 16 bits */
flags = get_be16(&ondisk->flags);
else
name = ondisk->name;
- if (!previous_name) {
- /* v3 and earlier */
- if (len == CE_NAMEMASK)
- len = strlen(name);
- ce = cache_entry_from_ondisk(mem_pool, ondisk, flags, name, len);
+ if (expand_name_field) {
+ const unsigned char *cp = (const unsigned char *)name;
+ size_t strip_len, previous_len;
+
+ /* If we're at the begining of a block, ignore the previous name */
+ strip_len = decode_varint(&cp);
+ if (previous_ce) {
+ previous_len = previous_ce->ce_namelen;
+ if (previous_len < strip_len)
+ die(_("malformed name field in the index, near path '%s'"),
+ previous_ce->name);
+ copy_len = previous_len - strip_len;
+ }
+ name = (const char *)cp;
+ }
- *ent_size = ondisk_ce_size(ce);
- } else {
- unsigned long consumed;
- consumed = expand_name_field(previous_name, name);
- ce = cache_entry_from_ondisk(mem_pool, ondisk, flags,
- previous_name->buf,
- previous_name->len);
+ if (len == CE_NAMEMASK) {
+ len = strlen(name);
+ if (expand_name_field)
+ len += copy_len;
+ }
+
+ ce = mem_pool__ce_alloc(ce_mem_pool, len);
+
+ ce->ce_stat_data.sd_ctime.sec = get_be32(&ondisk->ctime.sec);
+ ce->ce_stat_data.sd_mtime.sec = get_be32(&ondisk->mtime.sec);
+ ce->ce_stat_data.sd_ctime.nsec = get_be32(&ondisk->ctime.nsec);
+ ce->ce_stat_data.sd_mtime.nsec = get_be32(&ondisk->mtime.nsec);
+ ce->ce_stat_data.sd_dev = get_be32(&ondisk->dev);
+ ce->ce_stat_data.sd_ino = get_be32(&ondisk->ino);
+ ce->ce_mode = get_be32(&ondisk->mode);
+ ce->ce_stat_data.sd_uid = get_be32(&ondisk->uid);
+ ce->ce_stat_data.sd_gid = get_be32(&ondisk->gid);
+ ce->ce_stat_data.sd_size = get_be32(&ondisk->size);
+ ce->ce_flags = flags & ~CE_NAMEMASK;
+ ce->ce_namelen = len;
+ ce->index = 0;
+ hashcpy(ce->oid.hash, ondisk->sha1);
- *ent_size = (name - ((char *)ondisk)) + consumed;
+ if (expand_name_field) {
+ if (copy_len)
+ memcpy(ce->name, previous_ce->name, copy_len);
+ memcpy(ce->name + copy_len, name, len + 1 - copy_len);
+ *ent_size = (name - ((char *)ondisk)) + len + 1 - copy_len;
+ } else {
+ memcpy(ce->name, name, len + 1);
+ *ent_size = ondisk_ce_size(ce);
}
return ce;
}
return ondisk_size + entries * per_entry;
}
+struct index_entry_offset
+{
+ /* starting byte offset into index file, count of index entries in this block */
+ int offset, nr;
+};
+
+struct index_entry_offset_table
+{
+ int nr;
+ struct index_entry_offset entries[FLEX_ARRAY];
+};
+
+static struct index_entry_offset_table *read_ieot_extension(const char *mmap, size_t mmap_size, size_t offset);
+static void write_ieot_extension(struct strbuf *sb, struct index_entry_offset_table *ieot);
+
+static size_t read_eoie_extension(const char *mmap, size_t mmap_size);
+static void write_eoie_extension(struct strbuf *sb, git_hash_ctx *eoie_context, size_t offset);
+
+struct load_index_extensions
+{
+ pthread_t pthread;
+ struct index_state *istate;
+ const char *mmap;
+ size_t mmap_size;
+ unsigned long src_offset;
+};
+
+static void *load_index_extensions(void *_data)
+{
+ struct load_index_extensions *p = _data;
+ unsigned long src_offset = p->src_offset;
+
+ while (src_offset <= p->mmap_size - the_hash_algo->rawsz - 8) {
+ /* After an array of active_nr index entries,
+ * there can be arbitrary number of extended
+ * sections, each of which is prefixed with
+ * extension name (4-byte) and section length
+ * in 4-byte network byte order.
+ */
+ uint32_t extsize = get_be32(p->mmap + src_offset + 4);
+ if (read_index_extension(p->istate,
+ p->mmap + src_offset,
+ p->mmap + src_offset + 8,
+ extsize) < 0) {
+ munmap((void *)p->mmap, p->mmap_size);
+ die(_("index file corrupt"));
+ }
+ src_offset += 8;
+ src_offset += extsize;
+ }
+
+ return NULL;
+}
+
+/*
+ * A helper function that will load the specified range of cache entries
+ * from the memory mapped file and add them to the given index.
+ */
+static unsigned long load_cache_entry_block(struct index_state *istate,
+ struct mem_pool *ce_mem_pool, int offset, int nr, const char *mmap,
+ unsigned long start_offset, const struct cache_entry *previous_ce)
+{
+ int i;
+ unsigned long src_offset = start_offset;
+
+ for (i = offset; i < offset + nr; i++) {
+ struct ondisk_cache_entry *disk_ce;
+ struct cache_entry *ce;
+ unsigned long consumed;
+
+ disk_ce = (struct ondisk_cache_entry *)(mmap + src_offset);
+ ce = create_from_disk(ce_mem_pool, istate->version, disk_ce, &consumed, previous_ce);
+ set_index_entry(istate, i, ce);
+
+ src_offset += consumed;
+ previous_ce = ce;
+ }
+ return src_offset - start_offset;
+}
+
+static unsigned long load_all_cache_entries(struct index_state *istate,
+ const char *mmap, size_t mmap_size, unsigned long src_offset)
+{
+ unsigned long consumed;
+
+ if (istate->version == 4) {
+ mem_pool_init(&istate->ce_mem_pool,
+ estimate_cache_size_from_compressed(istate->cache_nr));
+ } else {
+ mem_pool_init(&istate->ce_mem_pool,
+ estimate_cache_size(mmap_size, istate->cache_nr));
+ }
+
+ consumed = load_cache_entry_block(istate, istate->ce_mem_pool,
+ 0, istate->cache_nr, mmap, src_offset, NULL);
+ return consumed;
+}
+
+/*
+ * Mostly randomly chosen maximum thread counts: we
+ * cap the parallelism to online_cpus() threads, and we want
+ * to have at least 10000 cache entries per thread for it to
+ * be worth starting a thread.
+ */
+
+#define THREAD_COST (10000)
+
+struct load_cache_entries_thread_data
+{
+ pthread_t pthread;
+ struct index_state *istate;
+ struct mem_pool *ce_mem_pool;
+ int offset;
+ const char *mmap;
+ struct index_entry_offset_table *ieot;
+ int ieot_start; /* starting index into the ieot array */
+ int ieot_blocks; /* count of ieot entries to process */
+ unsigned long consumed; /* return # of bytes in index file processed */
+};
+
+/*
+ * A thread proc to run the load_cache_entries() computation
+ * across multiple background threads.
+ */
+static void *load_cache_entries_thread(void *_data)
+{
+ struct load_cache_entries_thread_data *p = _data;
+ int i;
+
+ /* iterate across all ieot blocks assigned to this thread */
+ for (i = p->ieot_start; i < p->ieot_start + p->ieot_blocks; i++) {
+ p->consumed += load_cache_entry_block(p->istate, p->ce_mem_pool,
+ p->offset, p->ieot->entries[i].nr, p->mmap, p->ieot->entries[i].offset, NULL);
+ p->offset += p->ieot->entries[i].nr;
+ }
+ return NULL;
+}
+
+static unsigned long load_cache_entries_threaded(struct index_state *istate, const char *mmap, size_t mmap_size,
+ unsigned long src_offset, int nr_threads, struct index_entry_offset_table *ieot)
+{
+ int i, offset, ieot_blocks, ieot_start, err;
+ struct load_cache_entries_thread_data *data;
+ unsigned long consumed = 0;
+
+ /* a little sanity checking */
+ if (istate->name_hash_initialized)
+ BUG("the name hash isn't thread safe");
+
+ mem_pool_init(&istate->ce_mem_pool, 0);
+
+ /* ensure we have no more threads than we have blocks to process */
+ if (nr_threads > ieot->nr)
+ nr_threads = ieot->nr;
+ data = xcalloc(nr_threads, sizeof(*data));
+
+ offset = ieot_start = 0;
+ ieot_blocks = DIV_ROUND_UP(ieot->nr, nr_threads);
+ for (i = 0; i < nr_threads; i++) {
+ struct load_cache_entries_thread_data *p = &data[i];
+ int nr, j;
+
+ if (ieot_start + ieot_blocks > ieot->nr)
+ ieot_blocks = ieot->nr - ieot_start;
+
+ p->istate = istate;
+ p->offset = offset;
+ p->mmap = mmap;
+ p->ieot = ieot;
+ p->ieot_start = ieot_start;
+ p->ieot_blocks = ieot_blocks;
+
+ /* create a mem_pool for each thread */
+ nr = 0;
+ for (j = p->ieot_start; j < p->ieot_start + p->ieot_blocks; j++)
+ nr += p->ieot->entries[j].nr;
+ if (istate->version == 4) {
+ mem_pool_init(&p->ce_mem_pool,
+ estimate_cache_size_from_compressed(nr));
+ } else {
+ mem_pool_init(&p->ce_mem_pool,
+ estimate_cache_size(mmap_size, nr));
+ }
+
+ err = pthread_create(&p->pthread, NULL, load_cache_entries_thread, p);
+ if (err)
+ die(_("unable to create load_cache_entries thread: %s"), strerror(err));
+
+ /* increment by the number of cache entries in the ieot block being processed */
+ for (j = 0; j < ieot_blocks; j++)
+ offset += ieot->entries[ieot_start + j].nr;
+ ieot_start += ieot_blocks;
+ }
+
+ for (i = 0; i < nr_threads; i++) {
+ struct load_cache_entries_thread_data *p = &data[i];
+
+ err = pthread_join(p->pthread, NULL);
+ if (err)
+ die(_("unable to join load_cache_entries thread: %s"), strerror(err));
+ mem_pool_combine(istate->ce_mem_pool, p->ce_mem_pool);
+ consumed += p->consumed;
+ }
+
+ free(data);
+
+ return consumed;
+}
+
/* remember to discard_cache() before reading a different cache! */
int do_read_index(struct index_state *istate, const char *path, int must_exist)
{
- int fd, i;
+ int fd;
struct stat st;
unsigned long src_offset;
- struct cache_header *hdr;
- void *mmap;
+ const struct cache_header *hdr;
+ const char *mmap;
size_t mmap_size;
- struct strbuf previous_name_buf = STRBUF_INIT, *previous_name;
+ struct load_index_extensions p;
+ size_t extension_offset = 0;
+ int nr_threads, cpus;
+ struct index_entry_offset_table *ieot = NULL;
if (istate->initialized)
return istate->cache_nr;
die_errno("unable to map index file");
close(fd);
- hdr = mmap;
+ hdr = (const struct cache_header *)mmap;
if (verify_hdr(hdr, mmap_size) < 0)
goto unmap;
istate->cache = xcalloc(istate->cache_alloc, sizeof(*istate->cache));
istate->initialized = 1;
- if (istate->version == 4) {
- previous_name = &previous_name_buf;
- mem_pool_init(&istate->ce_mem_pool,
- estimate_cache_size_from_compressed(istate->cache_nr));
- } else {
- previous_name = NULL;
- mem_pool_init(&istate->ce_mem_pool,
- estimate_cache_size(mmap_size, istate->cache_nr));
- }
+ p.istate = istate;
+ p.mmap = mmap;
+ p.mmap_size = mmap_size;
src_offset = sizeof(*hdr);
- for (i = 0; i < istate->cache_nr; i++) {
- struct ondisk_cache_entry *disk_ce;
- struct cache_entry *ce;
- unsigned long consumed;
- disk_ce = (struct ondisk_cache_entry *)((char *)mmap + src_offset);
- ce = create_from_disk(istate->ce_mem_pool, disk_ce, &consumed, previous_name);
- set_index_entry(istate, i, ce);
+ if (git_config_get_index_threads(&nr_threads))
+ nr_threads = 1;
- src_offset += consumed;
+ /* TODO: does creating more threads than cores help? */
+ if (!nr_threads) {
+ nr_threads = istate->cache_nr / THREAD_COST;
+ cpus = online_cpus();
+ if (nr_threads > cpus)
+ nr_threads = cpus;
}
- strbuf_release(&previous_name_buf);
+
+ if (!HAVE_THREADS)
+ nr_threads = 1;
+
+ if (nr_threads > 1) {
+ extension_offset = read_eoie_extension(mmap, mmap_size);
+ if (extension_offset) {
+ int err;
+
+ p.src_offset = extension_offset;
+ err = pthread_create(&p.pthread, NULL, load_index_extensions, &p);
+ if (err)
+ die(_("unable to create load_index_extensions thread: %s"), strerror(err));
+
+ nr_threads--;
+ }
+ }
+
+ /*
+ * Locate and read the index entry offset table so that we can use it
+ * to multi-thread the reading of the cache entries.
+ */
+ if (extension_offset && nr_threads > 1)
+ ieot = read_ieot_extension(mmap, mmap_size, extension_offset);
+
+ if (ieot) {
+ src_offset += load_cache_entries_threaded(istate, mmap, mmap_size, src_offset, nr_threads, ieot);
+ free(ieot);
+ } else {
+ src_offset += load_all_cache_entries(istate, mmap, mmap_size, src_offset);
+ }
+
istate->timestamp.sec = st.st_mtime;
istate->timestamp.nsec = ST_MTIME_NSEC(st);
- while (src_offset <= mmap_size - the_hash_algo->rawsz - 8) {
- /* After an array of active_nr index entries,
- * there can be arbitrary number of extended
- * sections, each of which is prefixed with
- * extension name (4-byte) and section length
- * in 4-byte network byte order.
- */
- uint32_t extsize;
- memcpy(&extsize, (char *)mmap + src_offset + 4, 4);
- extsize = ntohl(extsize);
- if (read_index_extension(istate,
- (const char *) mmap + src_offset,
- (char *) mmap + src_offset + 8,
- extsize) < 0)
- goto unmap;
- src_offset += 8;
- src_offset += extsize;
+ /* if we created a thread, join it otherwise load the extensions on the primary thread */
+ if (extension_offset) {
+ int ret = pthread_join(p.pthread, NULL);
+ if (ret)
+ die(_("unable to join load_index_extensions thread: %s"), strerror(ret));
+ } else {
+ p.src_offset = src_offset;
+ load_index_extensions(&p);
}
- munmap(mmap, mmap_size);
+ munmap((void *)mmap, mmap_size);
return istate->cache_nr;
unmap:
- munmap(mmap, mmap_size);
+ munmap((void *)mmap, mmap_size);
die("index file corrupt");
}
int read_index_from(struct index_state *istate, const char *path,
const char *gitdir)
{
- uint64_t start = getnanotime();
struct split_index *split_index;
int ret;
char *base_oid_hex;
if (istate->initialized)
return istate->cache_nr;
+ trace_performance_enter();
ret = do_read_index(istate, path, 0);
- trace_performance_since(start, "read cache %s", path);
+ trace_performance_leave("read cache %s", path);
split_index = istate->split_index;
if (!split_index || is_null_oid(&split_index->base_oid)) {
return ret;
}
+ trace_performance_enter();
if (split_index->base)
discard_index(split_index->base);
else
base_oid_hex = oid_to_hex(&split_index->base_oid);
base_path = xstrfmt("%s/sharedindex.%s", gitdir, base_oid_hex);
ret = do_read_index(split_index->base, base_path, 1);
- if (oidcmp(&split_index->base_oid, &split_index->base->oid))
+ if (!oideq(&split_index->base_oid, &split_index->base->oid))
die("broken index, expect %s in %s, got %s",
base_oid_hex, base_path,
oid_to_hex(&split_index->base->oid));
freshen_shared_index(base_path, 0);
merge_base_index(istate);
post_read_index_from(istate);
- trace_performance_since(start, "read cache %s", base_path);
+ trace_performance_leave("read cache %s", base_path);
free(base_path);
return ret;
}
return 0;
}
-int index_has_changes(const struct index_state *istate,
+int index_has_changes(struct index_state *istate,
struct tree *tree,
struct strbuf *sb)
{
if (tree || !get_oid_tree("HEAD", &cmp)) {
struct diff_options opt;
- diff_setup(&opt);
+ repo_diff_setup(the_repository, &opt);
opt.flags.exit_with_status = 1;
if (!sb)
opt.flags.quick = 1;
return 0;
}
-static int write_index_ext_header(git_hash_ctx *context, int fd,
- unsigned int ext, unsigned int sz)
+static int write_index_ext_header(git_hash_ctx *context, git_hash_ctx *eoie_context,
+ int fd, unsigned int ext, unsigned int sz)
{
ext = htonl(ext);
sz = htonl(sz);
+ if (eoie_context) {
+ the_hash_algo->update_fn(eoie_context, &ext, 4);
+ the_hash_algo->update_fn(eoie_context, &sz, 4);
+ }
return ((ce_write(context, fd, &ext, 4) < 0) ||
(ce_write(context, fd, &sz, 4) < 0)) ? -1 : 0;
}
return (write_in_full(fd, write_buffer, left) < 0) ? -1 : 0;
}
-static void ce_smudge_racily_clean_entry(struct cache_entry *ce)
+static void ce_smudge_racily_clean_entry(struct index_state *istate,
+ struct cache_entry *ce)
{
/*
* The only thing we care about in this function is to smudge the
return;
if (ce_match_stat_basic(ce, &st))
return;
- if (ce_modified_check_fs(ce, &st)) {
+ if (ce_modified_check_fs(istate, ce, &st)) {
/* This is "racily clean"; smudge it. Note that this
* is a tricky code. At first glance, it may appear
* that it can break with this sequence:
if (n != the_hash_algo->rawsz)
goto out;
- if (hashcmp(istate->oid.hash, hash))
+ if (!hasheq(istate->oid.hash, hash))
goto out;
close(fd);
rollback_lock_file(lockfile);
}
+static int record_eoie(void)
+{
+ int val;
+
+ if (!git_config_get_bool("index.recordendofindexentries", &val))
+ return val;
+
+ /*
+ * As a convenience, the end of index entries extension
+ * used for threading is written by default if the user
+ * explicitly requested threaded index reads.
+ */
+ return !git_config_get_index_threads(&val) && val != 1;
+}
+
+static int record_ieot(void)
+{
+ int val;
+
+ if (!git_config_get_bool("index.recordoffsettable", &val))
+ return val;
+
+ /*
+ * As a convenience, the offset table used for threading is
+ * written by default if the user explicitly requested
+ * threaded index reads.
+ */
+ return !git_config_get_index_threads(&val) && val != 1;
+}
+
/*
* On success, `tempfile` is closed. If it is the temporary file
* of a `struct lock_file`, we will therefore effectively perform
{
uint64_t start = getnanotime();
int newfd = tempfile->fd;
- git_hash_ctx c;
+ git_hash_ctx c, eoie_c;
struct cache_header hdr;
int i, err = 0, removed, extended, hdr_version;
struct cache_entry **cache = istate->cache;
struct ondisk_cache_entry_extended ondisk;
struct strbuf previous_name_buf = STRBUF_INIT, *previous_name;
int drop_cache_tree = istate->drop_cache_tree;
+ off_t offset;
+ int ieot_entries = 1;
+ struct index_entry_offset_table *ieot = NULL;
+ int nr, nr_threads;
for (i = removed = extended = 0; i < entries; i++) {
if (cache[i]->ce_flags & CE_REMOVE)
if (ce_write(&c, newfd, &hdr, sizeof(hdr)) < 0)
return -1;
+ if (!HAVE_THREADS || git_config_get_index_threads(&nr_threads))
+ nr_threads = 1;
+
+ if (nr_threads != 1 && record_ieot()) {
+ int ieot_blocks, cpus;
+
+ /*
+ * ensure default number of ieot blocks maps evenly to the
+ * default number of threads that will process them leaving
+ * room for the thread to load the index extensions.
+ */
+ if (!nr_threads) {
+ ieot_blocks = istate->cache_nr / THREAD_COST;
+ cpus = online_cpus();
+ if (ieot_blocks > cpus - 1)
+ ieot_blocks = cpus - 1;
+ } else {
+ ieot_blocks = nr_threads;
+ if (ieot_blocks > istate->cache_nr)
+ ieot_blocks = istate->cache_nr;
+ }
+
+ /*
+ * no reason to write out the IEOT extension if we don't
+ * have enough blocks to utilize multi-threading
+ */
+ if (ieot_blocks > 1) {
+ ieot = xcalloc(1, sizeof(struct index_entry_offset_table)
+ + (ieot_blocks * sizeof(struct index_entry_offset)));
+ ieot_entries = DIV_ROUND_UP(entries, ieot_blocks);
+ }
+ }
+
+ offset = lseek(newfd, 0, SEEK_CUR);
+ if (offset < 0) {
+ free(ieot);
+ return -1;
+ }
+ offset += write_buffer_len;
+ nr = 0;
previous_name = (hdr_version == 4) ? &previous_name_buf : NULL;
for (i = 0; i < entries; i++) {
if (ce->ce_flags & CE_REMOVE)
continue;
if (!ce_uptodate(ce) && is_racy_timestamp(istate, ce))
- ce_smudge_racily_clean_entry(ce);
+ ce_smudge_racily_clean_entry(istate, ce);
if (is_null_oid(&ce->oid)) {
static const char msg[] = "cache entry has null sha1: %s";
static int allow = -1;
drop_cache_tree = 1;
}
+ if (ieot && i && (i % ieot_entries == 0)) {
+ ieot->entries[ieot->nr].nr = nr;
+ ieot->entries[ieot->nr].offset = offset;
+ ieot->nr++;
+ /*
+ * If we have a V4 index, set the first byte to an invalid
+ * character to ensure there is nothing common with the previous
+ * entry
+ */
+ if (previous_name)
+ previous_name->buf[0] = 0;
+ nr = 0;
+ offset = lseek(newfd, 0, SEEK_CUR);
+ if (offset < 0) {
+ free(ieot);
+ return -1;
+ }
+ offset += write_buffer_len;
+ }
if (ce_write_entry(&c, newfd, ce, previous_name, (struct ondisk_cache_entry *)&ondisk) < 0)
err = -1;
if (err)
break;
+ nr++;
+ }
+ if (ieot && nr) {
+ ieot->entries[ieot->nr].nr = nr;
+ ieot->entries[ieot->nr].offset = offset;
+ ieot->nr++;
}
strbuf_release(&previous_name_buf);
- if (err)
+ if (err) {
+ free(ieot);
return err;
+ }
/* Write extension data here */
+ offset = lseek(newfd, 0, SEEK_CUR);
+ if (offset < 0) {
+ free(ieot);
+ return -1;
+ }
+ offset += write_buffer_len;
+ the_hash_algo->init_fn(&eoie_c);
+
+ /*
+ * Lets write out CACHE_EXT_INDEXENTRYOFFSETTABLE first so that we
+ * can minimize the number of extensions we have to scan through to
+ * find it during load. Write it out regardless of the
+ * strip_extensions parameter as we need it when loading the shared
+ * index.
+ */
+ if (ieot) {
+ struct strbuf sb = STRBUF_INIT;
+
+ write_ieot_extension(&sb, ieot);
+ err = write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_INDEXENTRYOFFSETTABLE, sb.len) < 0
+ || ce_write(&c, newfd, sb.buf, sb.len) < 0;
+ strbuf_release(&sb);
+ free(ieot);
+ if (err)
+ return -1;
+ }
+
if (!strip_extensions && istate->split_index) {
struct strbuf sb = STRBUF_INIT;
err = write_link_extension(&sb, istate) < 0 ||
- write_index_ext_header(&c, newfd, CACHE_EXT_LINK,
+ write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_LINK,
sb.len) < 0 ||
ce_write(&c, newfd, sb.buf, sb.len) < 0;
strbuf_release(&sb);
struct strbuf sb = STRBUF_INIT;
cache_tree_write(&sb, istate->cache_tree);
- err = write_index_ext_header(&c, newfd, CACHE_EXT_TREE, sb.len) < 0
+ err = write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_TREE, sb.len) < 0
|| ce_write(&c, newfd, sb.buf, sb.len) < 0;
strbuf_release(&sb);
if (err)
struct strbuf sb = STRBUF_INIT;
resolve_undo_write(&sb, istate->resolve_undo);
- err = write_index_ext_header(&c, newfd, CACHE_EXT_RESOLVE_UNDO,
+ err = write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_RESOLVE_UNDO,
sb.len) < 0
|| ce_write(&c, newfd, sb.buf, sb.len) < 0;
strbuf_release(&sb);
struct strbuf sb = STRBUF_INIT;
write_untracked_extension(&sb, istate->untracked);
- err = write_index_ext_header(&c, newfd, CACHE_EXT_UNTRACKED,
+ err = write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_UNTRACKED,
sb.len) < 0 ||
ce_write(&c, newfd, sb.buf, sb.len) < 0;
strbuf_release(&sb);
struct strbuf sb = STRBUF_INIT;
write_fsmonitor_extension(&sb, istate);
- err = write_index_ext_header(&c, newfd, CACHE_EXT_FSMONITOR, sb.len) < 0
+ err = write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_FSMONITOR, sb.len) < 0
+ || ce_write(&c, newfd, sb.buf, sb.len) < 0;
+ strbuf_release(&sb);
+ if (err)
+ return -1;
+ }
+
+ /*
+ * CACHE_EXT_ENDOFINDEXENTRIES must be written as the last entry before the SHA1
+ * so that it can be found and processed before all the index entries are
+ * read. Write it out regardless of the strip_extensions parameter as we need it
+ * when loading the shared index.
+ */
+ if (offset && record_eoie()) {
+ struct strbuf sb = STRBUF_INIT;
+
+ write_eoie_extension(&sb, &eoie_c, offset);
+ err = write_index_ext_header(&c, NULL, newfd, CACHE_EXT_ENDOFINDEXENTRIES, sb.len) < 0
|| ce_write(&c, newfd, sb.buf, sb.len) < 0;
strbuf_release(&sb);
if (err)
int new_shared_index, ret;
struct split_index *si = istate->split_index;
+ if (git_env_bool("GIT_TEST_CHECK_CACHE_TREE", 0))
+ cache_tree_verify(istate);
+
if ((flags & SKIP_IF_UNCHANGED) && !istate->cache_changed) {
if (flags & COMMIT_LOCK)
rollback_lock_file(lock);
struct tempfile *temp;
int saved_errno;
- temp = mks_tempfile(git_path("sharedindex_XXXXXX"));
+ /* Same initial permissions as the main .git/index file */
+ temp = mks_tempfile_sm(git_path("sharedindex_XXXXXX"), 0, 0666);
if (!temp) {
oidclr(&si->base_oid);
ret = do_write_locked_index(istate, lock, flags);
{
dst->untracked = src->untracked;
src->untracked = NULL;
+ dst->cache_tree = src->cache_tree;
+ src->cache_tree = NULL;
}
struct cache_entry *dup_cache_entry(const struct cache_entry *ce,
return validate_index_cache_entries;
}
+
+#define EOIE_SIZE (4 + GIT_SHA1_RAWSZ) /* <4-byte offset> + <20-byte hash> */
+#define EOIE_SIZE_WITH_HEADER (4 + 4 + EOIE_SIZE) /* <4-byte signature> + <4-byte length> + EOIE_SIZE */
+
+static size_t read_eoie_extension(const char *mmap, size_t mmap_size)
+{
+ /*
+ * The end of index entries (EOIE) extension is guaranteed to be last
+ * so that it can be found by scanning backwards from the EOF.
+ *
+ * "EOIE"
+ * <4-byte length>
+ * <4-byte offset>
+ * <20-byte hash>
+ */
+ const char *index, *eoie;
+ uint32_t extsize;
+ size_t offset, src_offset;
+ unsigned char hash[GIT_MAX_RAWSZ];
+ git_hash_ctx c;
+
+ /* ensure we have an index big enough to contain an EOIE extension */
+ if (mmap_size < sizeof(struct cache_header) + EOIE_SIZE_WITH_HEADER + the_hash_algo->rawsz)
+ return 0;
+
+ /* validate the extension signature */
+ index = eoie = mmap + mmap_size - EOIE_SIZE_WITH_HEADER - the_hash_algo->rawsz;
+ if (CACHE_EXT(index) != CACHE_EXT_ENDOFINDEXENTRIES)
+ return 0;
+ index += sizeof(uint32_t);
+
+ /* validate the extension size */
+ extsize = get_be32(index);
+ if (extsize != EOIE_SIZE)
+ return 0;
+ index += sizeof(uint32_t);
+
+ /*
+ * Validate the offset we're going to look for the first extension
+ * signature is after the index header and before the eoie extension.
+ */
+ offset = get_be32(index);
+ if (mmap + offset < mmap + sizeof(struct cache_header))
+ return 0;
+ if (mmap + offset >= eoie)
+ return 0;
+ index += sizeof(uint32_t);
+
+ /*
+ * The hash is computed over extension types and their sizes (but not
+ * their contents). E.g. if we have "TREE" extension that is N-bytes
+ * long, "REUC" extension that is M-bytes long, followed by "EOIE",
+ * then the hash would be:
+ *
+ * SHA-1("TREE" + <binary representation of N> +
+ * "REUC" + <binary representation of M>)
+ */
+ src_offset = offset;
+ the_hash_algo->init_fn(&c);
+ while (src_offset < mmap_size - the_hash_algo->rawsz - EOIE_SIZE_WITH_HEADER) {
+ /* After an array of active_nr index entries,
+ * there can be arbitrary number of extended
+ * sections, each of which is prefixed with
+ * extension name (4-byte) and section length
+ * in 4-byte network byte order.
+ */
+ uint32_t extsize;
+ memcpy(&extsize, mmap + src_offset + 4, 4);
+ extsize = ntohl(extsize);
+
+ /* verify the extension size isn't so large it will wrap around */
+ if (src_offset + 8 + extsize < src_offset)
+ return 0;
+
+ the_hash_algo->update_fn(&c, mmap + src_offset, 8);
+
+ src_offset += 8;
+ src_offset += extsize;
+ }
+ the_hash_algo->final_fn(hash, &c);
+ if (!hasheq(hash, (const unsigned char *)index))
+ return 0;
+
+ /* Validate that the extension offsets returned us back to the eoie extension. */
+ if (src_offset != mmap_size - the_hash_algo->rawsz - EOIE_SIZE_WITH_HEADER)
+ return 0;
+
+ return offset;
+}
+
+static void write_eoie_extension(struct strbuf *sb, git_hash_ctx *eoie_context, size_t offset)
+{
+ uint32_t buffer;
+ unsigned char hash[GIT_MAX_RAWSZ];
+
+ /* offset */
+ put_be32(&buffer, offset);
+ strbuf_add(sb, &buffer, sizeof(uint32_t));
+
+ /* hash */
+ the_hash_algo->final_fn(hash, eoie_context);
+ strbuf_add(sb, hash, the_hash_algo->rawsz);
+}
+
+#define IEOT_VERSION (1)
+
+static struct index_entry_offset_table *read_ieot_extension(const char *mmap, size_t mmap_size, size_t offset)
+{
+ const char *index = NULL;
+ uint32_t extsize, ext_version;
+ struct index_entry_offset_table *ieot;
+ int i, nr;
+
+ /* find the IEOT extension */
+ if (!offset)
+ return NULL;
+ while (offset <= mmap_size - the_hash_algo->rawsz - 8) {
+ extsize = get_be32(mmap + offset + 4);
+ if (CACHE_EXT((mmap + offset)) == CACHE_EXT_INDEXENTRYOFFSETTABLE) {
+ index = mmap + offset + 4 + 4;
+ break;
+ }
+ offset += 8;
+ offset += extsize;
+ }
+ if (!index)
+ return NULL;
+
+ /* validate the version is IEOT_VERSION */
+ ext_version = get_be32(index);
+ if (ext_version != IEOT_VERSION) {
+ error("invalid IEOT version %d", ext_version);
+ return NULL;
+ }
+ index += sizeof(uint32_t);
+
+ /* extension size - version bytes / bytes per entry */
+ nr = (extsize - sizeof(uint32_t)) / (sizeof(uint32_t) + sizeof(uint32_t));
+ if (!nr) {
+ error("invalid number of IEOT entries %d", nr);
+ return NULL;
+ }
+ ieot = xmalloc(sizeof(struct index_entry_offset_table)
+ + (nr * sizeof(struct index_entry_offset)));
+ ieot->nr = nr;
+ for (i = 0; i < nr; i++) {
+ ieot->entries[i].offset = get_be32(index);
+ index += sizeof(uint32_t);
+ ieot->entries[i].nr = get_be32(index);
+ index += sizeof(uint32_t);
+ }
+
+ return ieot;
+}
+
+static void write_ieot_extension(struct strbuf *sb, struct index_entry_offset_table *ieot)
+{
+ uint32_t buffer;
+ int i;
+
+ /* version */
+ put_be32(&buffer, IEOT_VERSION);
+ strbuf_add(sb, &buffer, sizeof(uint32_t));
+
+ /* ieot */
+ for (i = 0; i < ieot->nr; i++) {
+
+ /* offset */
+ put_be32(&buffer, ieot->entries[i].offset);
+ strbuf_add(sb, &buffer, sizeof(uint32_t));
+
+ /* count */
+ put_be32(&buffer, ieot->entries[i].nr);
+ strbuf_add(sb, &buffer, sizeof(uint32_t));
+ }
+}
#include "cache.h"
+#include "dir.h"
#include "repository.h"
#include "config.h"
#include "submodule-config.h"
const struct submodule_entry *b = entry_or_key;
return strcmp(a->config->path, b->config->path) ||
- oidcmp(&a->config->gitmodules_oid, &b->config->gitmodules_oid);
+ !oideq(&a->config->gitmodules_oid, &b->config->gitmodules_oid);
}
static int config_name_cmp(const void *unused_cmp_data,
const struct submodule_entry *b = entry_or_key;
return strcmp(a->config->name, b->config->name) ||
- oidcmp(&a->config->gitmodules_oid, &b->config->gitmodules_oid);
+ !oideq(&a->config->gitmodules_oid, &b->config->gitmodules_oid);
}
static struct submodule_cache *submodule_cache_alloc(void)
int overwrite;
};
+ /*
+ * Parse a config item from .gitmodules.
+ *
+ * This does not handle submodule-related configuration from the main
+ * config store (.git/config, etc). Callers are responsible for
+ * checking for overrides in the main config store when appropriate.
+ */
static int parse_config(const char *var, const char *value, void *data)
{
struct parse_config_parameter *me = data;
warn_multiple_config(me->treeish_name, submodule->name,
"update");
else if (parse_submodule_update_strategy(value,
- &submodule->update_strategy) < 0)
- die(_("invalid value for %s"), var);
+ &submodule->update_strategy) < 0 ||
+ submodule->update_strategy.type == SM_UPDATE_COMMAND)
+ die(_("invalid value for %s"), var);
} else if (!strcmp(item.buf, "shallow")) {
if (!me->overwrite && submodule->recommend_shallow != -1)
warn_multiple_config(me->treeish_name, submodule->name,
static void config_from_gitmodules(config_fn_t fn, struct repository *repo, void *data)
{
if (repo->worktree) {
- char *file = repo_worktree_path(repo, GITMODULES_FILE);
- git_config_from_file(fn, file, data);
+ struct git_config_source config_source = { 0 };
+ const struct config_options opts = { 0 };
+ struct object_id oid;
+ char *file;
+
+ file = repo_worktree_path(repo, GITMODULES_FILE);
+ if (file_exists(file)) {
+ config_source.file = file;
+ } else if (repo->submodule_prefix) {
+ /*
+ * When get_oid and config_with_options, used below,
+ * become able to work on a specific repository, this
+ * warning branch can be removed.
+ */
+ warning("nested submodules without %s in the working tree are not supported yet",
+ GITMODULES_FILE);
+ goto out;
+ } else if (get_oid(GITMODULES_INDEX, &oid) >= 0) {
+ config_source.blob = GITMODULES_INDEX;
+ } else if (get_oid(GITMODULES_HEAD, &oid) >= 0) {
+ config_source.blob = GITMODULES_HEAD;
+ } else {
+ goto out;
+ }
+
+ config_with_options(fn, data, &config_source, &opts);
+
+out:
free(file);
}
}
submodule_cache_clear(r->submodule_cache);
}
+static int config_print_callback(const char *var, const char *value, void *cb_data)
+{
+ char *wanted_key = cb_data;
+
+ if (!strcmp(wanted_key, var))
+ printf("%s\n", value);
+
+ return 0;
+}
+
+int print_config_from_gitmodules(struct repository *repo, const char *key)
+{
+ int ret;
+ char *store_key;
+
+ ret = git_config_parse_key(key, &store_key, NULL);
+ if (ret < 0)
+ return CONFIG_INVALID_KEY;
+
+ config_from_gitmodules(config_print_callback, repo, store_key);
+
+ free(store_key);
+ return 0;
+}
+
+int config_set_in_gitmodules_file_gently(const char *key, const char *value)
+{
+ int ret;
+
+ ret = git_config_set_in_file_gently(GITMODULES_FILE, key, value);
+ if (ret < 0)
+ /* Maybe the user already did that, don't error out here */
+ warning(_("Could not update .gitmodules entry %s"), key);
+
+ return ret;
+}
+
struct fetch_config {
int *max_children;
int *recurse_submodules;
#include "worktree.h"
#include "parse-options.h"
#include "object-store.h"
+#include "commit-reach.h"
static int config_update_recurse_submodules = RECURSE_SUBMODULES_OFF;
static struct string_list changed_submodule_names = STRING_LIST_INIT_DUP;
return 0;
}
+/*
+ * Check if the .gitmodules file is safe to write.
+ *
+ * Writing to the .gitmodules file requires that the file exists in the
+ * working tree or, if it doesn't, that a brand new .gitmodules file is going
+ * to be created (i.e. it's neither in the index nor in the current branch).
+ *
+ * It is not safe to write to .gitmodules if it's not in the working tree but
+ * it is in the index or in the current branch, because writing new values
+ * (and staging them) would blindly overwrite ALL the old content.
+ */
+int is_writing_gitmodules_ok(void)
+{
+ struct object_id oid;
+ return file_exists(GITMODULES_FILE) ||
+ (get_oid(GITMODULES_INDEX, &oid) < 0 && get_oid(GITMODULES_HEAD, &oid) < 0);
+}
+
/*
* Check if the .gitmodules file has unstaged modifications. This must be
* checked before allowing modifications to the .gitmodules file with the
{
struct strbuf entry = STRBUF_INIT;
const struct submodule *submodule;
+ int ret;
if (!file_exists(GITMODULES_FILE)) /* Do nothing without .gitmodules */
return -1;
strbuf_addstr(&entry, "submodule.");
strbuf_addstr(&entry, submodule->name);
strbuf_addstr(&entry, ".path");
- if (git_config_set_in_file_gently(GITMODULES_FILE, entry.buf, newpath) < 0) {
- /* Maybe the user already did that, don't error out here */
- warning(_("Could not update .gitmodules entry %s"), entry.buf);
- strbuf_release(&entry);
- return -1;
- }
+ ret = config_set_in_gitmodules_file_gently(entry.buf, newpath);
strbuf_release(&entry);
- return 0;
+ return ret;
}
/*
{
struct commit_list *list;
- init_revisions(rev, NULL);
+ repo_init_revisions(the_repository, rev, NULL);
setup_revisions(0, NULL, rev, NULL);
rev->left_right = 1;
rev->first_parent_only = 1;
fast_backward = 1;
}
- if (!oidcmp(one, two)) {
+ if (oideq(one, two)) {
strbuf_release(&sb);
return;
}
}
struct collect_changed_submodules_cb_data {
+ struct repository *repo;
struct string_list *changed;
const struct object_id *commit_oid;
};
if (!S_ISGITLINK(p->two->mode))
continue;
- submodule = submodule_from_path(the_repository,
+ submodule = submodule_from_path(me->repo,
commit_oid, p->two->path);
if (submodule)
name = submodule->name;
name = default_name_or_path(p->two->path);
/* make sure name does not collide with existing one */
if (name)
- submodule = submodule_from_name(the_repository,
+ submodule = submodule_from_name(me->repo,
commit_oid, name);
if (submodule) {
warning("Submodule in commit %s at path: "
* have a corresponding 'struct oid_array' (in the 'util' field) which lists
* what the submodule pointers were updated to during the change.
*/
-static void collect_changed_submodules(struct string_list *changed,
+static void collect_changed_submodules(struct repository *r,
+ struct string_list *changed,
struct argv_array *argv)
{
struct rev_info rev;
const struct commit *commit;
- init_revisions(&rev, NULL);
+ repo_init_revisions(r, &rev, NULL);
setup_revisions(argv->argc, argv->argv, &rev, NULL);
if (prepare_revision_walk(&rev))
die("revision walk setup failed");
while ((commit = get_revision(&rev))) {
struct rev_info diff_rev;
struct collect_changed_submodules_cb_data data;
+ data.repo = r;
data.changed = changed;
data.commit_oid = &commit->object.oid;
- init_revisions(&diff_rev, NULL);
+ repo_init_revisions(r, &diff_rev, NULL);
diff_rev.diffopt.output_format |= DIFF_FORMAT_CALLBACK;
diff_rev.diffopt.format_callback = collect_changed_submodules_cb;
diff_rev.diffopt.format_callback_data = &data;
}
struct has_commit_data {
+ struct repository *repo;
int result;
const char *path;
};
{
struct has_commit_data *cb = data;
- enum object_type type = oid_object_info(the_repository, oid, NULL);
+ enum object_type type = oid_object_info(cb->repo, oid, NULL);
switch (type) {
case OBJ_COMMIT:
}
}
-static int submodule_has_commits(const char *path, struct oid_array *commits)
+static int submodule_has_commits(struct repository *r,
+ const char *path,
+ struct oid_array *commits)
{
- struct has_commit_data has_commit = { 1, path };
+ struct has_commit_data has_commit = { r, 1, path };
/*
* Perform a cheap, but incorrect check for the existence of 'commits'.
return has_commit.result;
}
-static int submodule_needs_pushing(const char *path, struct oid_array *commits)
+static int submodule_needs_pushing(struct repository *r,
+ const char *path,
+ struct oid_array *commits)
{
- if (!submodule_has_commits(path, commits))
+ if (!submodule_has_commits(r, path, commits))
/*
* NOTE: We do consider it safe to return "no" here. The
* correct answer would be "We do not know" instead of
return 0;
}
-int find_unpushed_submodules(struct oid_array *commits,
- const char *remotes_name, struct string_list *needs_pushing)
+int find_unpushed_submodules(struct repository *r,
+ struct oid_array *commits,
+ const char *remotes_name,
+ struct string_list *needs_pushing)
{
struct string_list submodules = STRING_LIST_INIT_DUP;
struct string_list_item *name;
argv_array_push(&argv, "--not");
argv_array_pushf(&argv, "--remotes=%s", remotes_name);
- collect_changed_submodules(&submodules, &argv);
+ collect_changed_submodules(r, &submodules, &argv);
for_each_string_list_item(name, &submodules) {
struct oid_array *commits = name->util;
const struct submodule *submodule;
const char *path = NULL;
- submodule = submodule_from_name(the_repository, &null_oid, name->string);
+ submodule = submodule_from_name(r, &null_oid, name->string);
if (submodule)
path = submodule->path;
else
if (!path)
continue;
- if (submodule_needs_pushing(path, commits))
+ if (submodule_needs_pushing(r, path, commits))
string_list_insert(needs_pushing, path);
}
die("process for submodule '%s' failed", path);
}
-int push_unpushed_submodules(struct oid_array *commits,
+int push_unpushed_submodules(struct repository *r,
+ struct oid_array *commits,
const struct remote *remote,
const struct refspec *rs,
const struct string_list *push_options,
int i, ret = 1;
struct string_list needs_pushing = STRING_LIST_INIT_DUP;
- if (!find_unpushed_submodules(commits, remote->name, &needs_pushing))
+ if (!find_unpushed_submodules(r, commits,
+ remote->name, &needs_pushing))
return 1;
/*
oid_array_append(&ref_tips_after_fetch, oid);
}
-static void calculate_changed_submodule_paths(void)
+static void calculate_changed_submodule_paths(struct repository *r)
{
struct argv_array argv = ARGV_ARRAY_INIT;
struct string_list changed_submodules = STRING_LIST_INIT_DUP;
const struct string_list_item *name;
/* No need to check if there are no submodules configured */
- if (!submodule_from_path(the_repository, NULL, NULL))
+ if (!submodule_from_path(r, NULL, NULL))
return;
argv_array_push(&argv, "--"); /* argv[0] program name */
* Collect all submodules (whether checked out or not) for which new
* commits have been recorded upstream in "changed_submodule_names".
*/
- collect_changed_submodules(&changed_submodules, &argv);
+ collect_changed_submodules(r, &changed_submodules, &argv);
for_each_string_list_item(name, &changed_submodules) {
struct oid_array *commits = name->util;
const struct submodule *submodule;
const char *path = NULL;
- submodule = submodule_from_name(the_repository, &null_oid, name->string);
+ submodule = submodule_from_name(r, &null_oid, name->string);
if (submodule)
path = submodule->path;
else
if (!path)
continue;
- if (!submodule_has_commits(path, commits))
+ if (!submodule_has_commits(r, path, commits))
string_list_append(&changed_submodule_names, name->string);
}
initialized_fetch_ref_tips = 0;
}
-int submodule_touches_in_range(struct object_id *excl_oid,
+int submodule_touches_in_range(struct repository *r,
+ struct object_id *excl_oid,
struct object_id *incl_oid)
{
struct string_list subs = STRING_LIST_INIT_DUP;
int ret;
/* No need to check if there are no submodules configured */
- if (!submodule_from_path(the_repository, NULL, NULL))
+ if (!submodule_from_path(r, NULL, NULL))
return 0;
argv_array_push(&args, "--"); /* args[0] program name */
argv_array_push(&args, oid_to_hex(excl_oid));
}
- collect_changed_submodules(&subs, &args);
+ collect_changed_submodules(r, &subs, &args);
ret = subs.nr;
argv_array_clear(&args);
argv_array_push(&spf.args, "--recurse-submodules-default");
/* default value, "--submodule-prefix" and its value are added later */
- calculate_changed_submodule_paths();
+ calculate_changed_submodule_paths(r);
run_processes_parallel(max_parallel_jobs,
get_next_submodule,
fetch_start_failure,
return ret;
}
+ int validate_submodule_git_dir(char *git_dir, const char *submodule_name)
+ {
+ size_t len = strlen(git_dir), suffix_len = strlen(submodule_name);
+ char *p;
+ int ret = 0;
+
+ if (len <= suffix_len || (p = git_dir + len - suffix_len)[-1] != '/' ||
+ strcmp(p, submodule_name))
+ BUG("submodule name '%s' not a suffix of git dir '%s'",
+ submodule_name, git_dir);
+
+ /*
+ * We prevent the contents of sibling submodules' git directories to
+ * clash.
+ *
+ * Example: having a submodule named `hippo` and another one named
+ * `hippo/hooks` would result in the git directories
+ * `.git/modules/hippo/` and `.git/modules/hippo/hooks/`, respectively,
+ * but the latter directory is already designated to contain the hooks
+ * of the former.
+ */
+ for (; *p; p++) {
+ if (is_dir_sep(*p)) {
+ char c = *p;
+
+ *p = '\0';
+ if (is_git_directory(git_dir))
+ ret = -1;
+ *p = c;
+
+ if (ret < 0)
+ return error(_("submodule git dir '%s' is "
+ "inside git dir '%.*s'"),
+ git_dir,
+ (int)(p - git_dir), git_dir);
+ }
+ }
+
+ return 0;
+ }
+
/*
* Embeds a single submodules git directory into the superprojects git dir,
* non recursively.
const char *path)
{
char *old_git_dir = NULL, *real_old_git_dir = NULL, *real_new_git_dir = NULL;
- const char *new_git_dir;
+ char *new_git_dir;
const struct submodule *sub;
if (submodule_uses_worktrees(path))
if (!sub)
die(_("could not lookup name for submodule '%s'"), path);
- new_git_dir = git_path("modules/%s", sub->name);
+ new_git_dir = git_pathdup("modules/%s", sub->name);
+ if (validate_submodule_git_dir(new_git_dir, sub->name) < 0)
+ die(_("refusing to move '%s' into an existing git dir"),
+ real_old_git_dir);
if (safe_create_leading_directories_const(new_git_dir) < 0)
die(_("could not create directory '%s'"), new_git_dir);
real_new_git_dir = real_pathdup(new_git_dir, 1);
+ free(new_git_dir);
fprintf(stderr, _("Migrating git directory of '%s%s' from\n'%s' to\n'%s'\n"),
get_super_prefix_or_empty(), path,
#define SUBMODULE_UPDATE_STRATEGY_INIT {SM_UPDATE_UNSPECIFIED, NULL}
int is_gitmodules_unmerged(const struct index_state *istate);
+int is_writing_gitmodules_ok(void);
int is_staging_gitmodules_ok(struct index_state *istate);
int update_path_in_gitmodules(const char *oldpath, const char *newpath);
int remove_path_from_gitmodules(const char *path);
* Checks if there are submodule changes in a..b. If a is the null OID,
* checks b and all its ancestors instead.
*/
-int submodule_touches_in_range(struct object_id *a,
+int submodule_touches_in_range(struct repository *r,
+ struct object_id *a,
struct object_id *b);
-int find_unpushed_submodules(struct oid_array *commits,
+int find_unpushed_submodules(struct repository *r,
+ struct oid_array *commits,
const char *remotes_name,
struct string_list *needs_pushing);
struct refspec;
-int push_unpushed_submodules(struct oid_array *commits,
+int push_unpushed_submodules(struct repository *r,
+ struct oid_array *commits,
const struct remote *remote,
const struct refspec *rs,
const struct string_list *push_options,
*/
int submodule_to_gitdir(struct strbuf *buf, const char *submodule);
+ /*
+ * Make sure that no submodule's git dir is nested in a sibling submodule's.
+ */
+ int validate_submodule_git_dir(char *git_dir, const char *submodule_name);
+
#define SUBMODULE_MOVE_HEAD_DRY_RUN (1<<0)
#define SUBMODULE_MOVE_HEAD_FORCE (1<<1)
int submodule_move_head(const char *path,
test_must_fail test-tool path-utils absolute_path ""
'
+ test_expect_success MINGW '<drive-letter>:\\abc is an absolute path' '
+ for letter in : \" C Z 1 ä
+ do
+ path=$letter:\\abc &&
+ absolute="$(test-tool path-utils absolute_path "$path")" &&
+ test "$path" = "$absolute" || return 1
+ done
+ '
+
test_expect_success 'real path rejects the empty string' '
test_must_fail test-tool path-utils real_path ""
'
test_git_path GIT_COMMON_DIR=bar config bar/config
test_git_path GIT_COMMON_DIR=bar packed-refs bar/packed-refs
test_git_path GIT_COMMON_DIR=bar shallow bar/shallow
+test_git_path GIT_COMMON_DIR=bar common bar/common
+test_git_path GIT_COMMON_DIR=bar common/file bar/common/file
# In the tests below, $(pwd) must be used because it is a native path on
# Windows and avoids MSYS's path mangling (which simplifies "foo/../bar" and
~1000000 \
~9999999 \
\
+ .gitmodules:\$DATA \
+ "gitmod~4 . :\$DATA" \
+ \
--not \
".gitmodules x" \
".gitmodules .x" \
\
GI7EB~1 \
GI7EB~01 \
- GI7EB~1X
+ GI7EB~1X \
+ \
+ .gitmodules,:\$DATA
+ '
+
+ test_expect_success MINGW 'is_valid_path() on Windows' '
+ test-tool path-utils is_valid_path \
+ win32 \
+ "win32 x" \
+ ../hello.txt \
+ C:\\git \
+ \
+ --not \
+ "win32 " \
+ "win32 /x " \
+ "win32." \
+ "win32 . ." \
+ .../hello.txt \
+ colon:test
'
test_done
grep "HEAD points to something strange" out
'
+test_expect_success 'HEAD link pointing at a funny object (from different wt)' '
+ test_when_finished "mv .git/SAVED_HEAD .git/HEAD" &&
+ test_when_finished "rm -rf .git/worktrees wt" &&
+ git worktree add wt &&
+ mv .git/HEAD .git/SAVED_HEAD &&
+ echo $ZERO_OID >.git/HEAD &&
+ # avoid corrupt/broken HEAD from interfering with repo discovery
+ test_must_fail git -C wt fsck 2>out &&
+ grep "main-worktree/HEAD: detached HEAD points" out
+'
+
+test_expect_success 'other worktree HEAD link pointing at a funny object' '
+ test_when_finished "rm -rf .git/worktrees other" &&
+ git worktree add other &&
+ echo $ZERO_OID >.git/worktrees/other/HEAD &&
+ test_must_fail git fsck 2>out &&
+ grep "worktrees/other/HEAD: detached HEAD points" out
+'
+
+test_expect_success 'other worktree HEAD link pointing at missing object' '
+ test_when_finished "rm -rf .git/worktrees other" &&
+ git worktree add other &&
+ echo "Contents missing from repo" | git hash-object --stdin >.git/worktrees/other/HEAD &&
+ test_must_fail git fsck 2>out &&
+ grep "worktrees/other/HEAD: invalid sha1 pointer" out
+'
+
+test_expect_success 'other worktree HEAD link pointing at a funny place' '
+ test_when_finished "rm -rf .git/worktrees other" &&
+ git worktree add other &&
+ echo "ref: refs/funny/place" >.git/worktrees/other/HEAD &&
+ test_must_fail git fsck 2>out &&
+ grep "worktrees/other/HEAD points to something strange" out
+'
+
test_expect_success 'email without @ is okay' '
git cat-file commit HEAD >basis &&
sed "s/@/AT/" basis >okay &&
(
git init $name-$type &&
cd $name-$type &&
+ git config core.protectNTFS false &&
echo content >file &&
git add file &&
git commit -m base &&
)
'
- test_expect_success 'submodule update - command in .gitmodules is ignored' '
+ test_expect_success 'submodule update - command in .gitmodules is rejected' '
test_when_finished "git -C super reset --hard HEAD^" &&
git -C super config -f .gitmodules submodule.submodule.update "!false" &&
git -C super commit -a -m "add command to .gitmodules file" &&
git -C super/submodule reset --hard $submodulesha1^ &&
- git -C super submodule update submodule
+ test_must_fail git -C super submodule update submodule
+ '
+
+ test_expect_success 'fsck detects command in .gitmodules' '
+ git init command-in-gitmodules &&
+ (
+ cd command-in-gitmodules &&
+ git submodule add ../submodule submodule &&
+ test_commit adding-submodule &&
+
+ git config -f .gitmodules submodule.submodule.update "!false" &&
+ git add .gitmodules &&
+ test_commit configuring-update &&
+ test_must_fail git fsck
+ )
'
cat << EOF >expect
'
test_expect_success 'submodule init does not copy command into .git/config' '
+ test_when_finished "git -C super update-index --force-remove submodule1" &&
+ test_when_finished git config -f super/.gitmodules \
+ --remove-section submodule.submodule1 &&
(cd super &&
git ls-files -s submodule >out &&
H=$(cut -d" " -f2 out) &&
git config -f .gitmodules submodule.submodule1.path submodule1 &&
git config -f .gitmodules submodule.submodule1.url ../submodule &&
git config -f .gitmodules submodule.submodule1.update !false &&
- git submodule init submodule1 &&
- echo "none" >expect &&
- git config submodule.submodule1.update >actual &&
- test_cmp expect actual
+ test_must_fail git submodule init submodule1 &&
+ test_expect_code 1 git config submodule.submodule1.update >actual &&
+ test_must_be_empty actual
)
'
(cd .git/modules/deeper/submodule &&
git log > ../../../../actual
) &&
- test_cmp actual expected
+ test_cmp expected actual
)
'
(cd .git/modules/deeper/submodule &&
git log > ../../../../actual
) &&
- test_cmp actual expected
+ test_cmp expected actual
)
'
git add deeper/submodule &&
git commit -m "update submodule" &&
git push origin : &&
- test_cmp actual expected
+ test_cmp expected actual
)
'
(cd .git/modules/submodule/modules/subsubmodule &&
git log > ../../../../../actual
) &&
- test_cmp actual expected
+ test_cmp expected actual
)
'
INPUT_END
git fast-import <input &&
- test 8 = $(find .git/objects/pack -type f | wc -l) &&
+ test 8 = $(find .git/objects/pack -type f | grep -v multi-pack-index | wc -l) &&
test $(git rev-parse refs/tags/O3-2nd) = $(git rev-parse O3^) &&
git log --reverse --pretty=oneline O3 | sed s/^.*z// >actual &&
test_cmp expect actual
test_must_fail git fast-import <input
'
+ test_expect_success 'R: import-marks features forbidden by default' '
+ >git.marks &&
+ echo "feature import-marks=git.marks" >input &&
+ test_must_fail git fast-import <input &&
+ echo "feature import-marks-if-exists=git.marks" >input &&
+ test_must_fail git fast-import <input
+ '
+
test_expect_success 'R: only one import-marks feature allowed per stream' '
+ >git.marks &&
+ >git2.marks &&
cat >input <<-EOF &&
feature import-marks=git.marks
feature import-marks=git2.marks
EOF
+ test_must_fail git fast-import --allow-unsafe-features <input
+ '
+
+ test_expect_success 'R: export-marks feature forbidden by default' '
+ echo "feature export-marks=git.marks" >input &&
test_must_fail git fast-import <input
'
EOF
- cat input | git fast-import &&
+ git fast-import --allow-unsafe-features <input &&
grep :1 git.marks
'
test_expect_success 'R: export-marks options can be overridden by commandline options' '
- cat input | git fast-import --export-marks=other.marks &&
- grep :1 other.marks
+ cat >input <<-\EOF &&
+ feature export-marks=feature-sub/git.marks
+ blob
+ mark :1
+ data 3
+ hi
+
+ EOF
+ git fast-import --allow-unsafe-features \
+ --export-marks=cmdline-sub/other.marks <input &&
+ grep :1 cmdline-sub/other.marks &&
+ test_path_is_missing feature-sub
'
test_expect_success 'R: catch typo in marks file name' '
test_must_fail git fast-import --import-marks=nonexistent.marks </dev/null &&
echo "feature import-marks=nonexistent.marks" |
- test_must_fail git fast-import
+ test_must_fail git fast-import --allow-unsafe-features
'
test_expect_success 'R: import and output marks can be the same file' '
test_expect_success 'R: feature import-marks-if-exists' '
rm -f io.marks &&
- git fast-import --export-marks=io.marks <<-\EOF &&
+ git fast-import --export-marks=io.marks \
+ --allow-unsafe-features <<-\EOF &&
feature import-marks-if-exists=not_io.marks
EOF
test_must_be_empty io.marks &&
echo ":1 $blob" >expect &&
echo ":2 $blob" >>expect &&
- git fast-import --export-marks=io.marks <<-\EOF &&
+ git fast-import --export-marks=io.marks \
+ --allow-unsafe-features <<-\EOF &&
feature import-marks-if-exists=io.marks
blob
mark :2
echo ":3 $blob" >>expect &&
git fast-import --import-marks=io.marks \
- --export-marks=io.marks <<-\EOF &&
+ --export-marks=io.marks \
+ --allow-unsafe-features <<-\EOF &&
feature import-marks-if-exists=not_io.marks
blob
mark :3
test_cmp expect io.marks &&
git fast-import --import-marks-if-exists=not_io.marks \
- --export-marks=io.marks <<-\EOF &&
+ --export-marks=io.marks \
+ --allow-unsafe-features <<-\EOF &&
feature import-marks-if-exists=io.marks
EOF
test_must_be_empty io.marks
feature export-marks=marks.new
EOF
- cat input | git fast-import &&
+ git fast-import --allow-unsafe-features <input &&
test_cmp marks.out marks.new
'
feature export-marks=marks.new
EOF
- cat input | git fast-import --import-marks=marks.out &&
+ git fast-import --import-marks=marks.out --allow-unsafe-features <input &&
test_cmp marks.out marks.new
'
head -n2 marks.out > one.marks &&
tail -n +3 marks.out > two.marks &&
- git fast-import --import-marks=one.marks --import-marks=two.marks <input &&
+ git fast-import --import-marks=one.marks --import-marks=two.marks \
+ --allow-unsafe-features <input &&
test_cmp marks.out combined.marks
'
mkdir -p .git/info/fast-import/ &&
cp marks.new .git/info/fast-import/relative.in &&
- git fast-import <input &&
+ git fast-import --allow-unsafe-features <input &&
test_cmp marks.new .git/info/fast-import/relative.out
'
feature export-marks=non-relative.out
EOF
- git fast-import <input &&
+ git fast-import --allow-unsafe-features <input &&
test_cmp marks.new non-relative.out
'
EOF
- cat input | git fast-import 2> output &&
+ git fast-import 2>output <input &&
test_must_be_empty output
'
child_process_init(fastimport);
fastimport->in = helper->out;
argv_array_push(&fastimport->args, "fast-import");
+ argv_array_push(&fastimport->args, "--allow-unsafe-features");
argv_array_push(&fastimport->args, debug ? "--stats" : "--quiet");
if (data->bidi_import) {
fprintf(stderr, "Debug: Falling back to dumb "
"transport.\n");
} else {
- die(_(_("unknown response to connect: %s")),
+ die(_("unknown response to connect: %s"),
cmdbuf->buf);
}
}
static struct transport_vtable vtable = {
+ 0,
set_helper_option,
get_refs_list,
fetch,
strbuf_addstr(err, _("empty filename in tree entry"));
return -1;
}
+ #ifdef GIT_WINDOWS_NATIVE
+ if (protect_ntfs && strchr(path, '\\')) {
+ strbuf_addf(err, _("filename in tree entry contains backslash: '%s'"), path);
+ return -1;
+ }
+ #endif
len = strlen(path) + 1;
/* Initialize the descriptor entry */
* 5 | file | 1 | 1 | 0
* 6 | file | 1 | 2 | 0
* 7 | file | 2 | -1 | 2
- * 8 | file | 2 | 0 | 2
+ * 8 | file | 2 | 0 | 1
* 9 | file | 2 | 1 | 0
* 10 | file | 2 | 2 | -1
* -----+-------+----------+----------+-------
* 15 | dir | 1 | 1 | 1 (*)
* 16 | dir | 1 | 2 | 0
* 17 | dir | 2 | -1 | 2
- * 18 | dir | 2 | 0 | 2
+ * 18 | dir | 2 | 0 | 1
* 19 | dir | 2 | 1 | 1 (*)
* 20 | dir | 2 | 2 | -1
*
negative = do_match(entry, base, base_offset, ps, 1);
- /* #3, #4, #7, #8, #13, #14, #17, #18 */
+ /* #8, #18 */
+ if (positive == all_entries_interesting &&
+ negative == entry_not_interesting)
+ return entry_interesting;
+
+ /* #3, #4, #7, #13, #14, #17 */
if (negative <= entry_not_interesting)
return positive;
return start_delayed_progress(_("Checking out files"), total);
}
+static void setup_collided_checkout_detection(struct checkout *state,
+ struct index_state *index)
+{
+ int i;
+
+ state->clone = 1;
+ for (i = 0; i < index->cache_nr; i++)
+ index->cache[i]->ce_flags &= ~CE_MATCHED;
+}
+
+static void report_collided_checkout(struct index_state *index)
+{
+ struct string_list list = STRING_LIST_INIT_NODUP;
+ int i;
+
+ for (i = 0; i < index->cache_nr; i++) {
+ struct cache_entry *ce = index->cache[i];
+
+ if (!(ce->ce_flags & CE_MATCHED))
+ continue;
+
+ string_list_append(&list, ce->name);
+ ce->ce_flags &= ~CE_MATCHED;
+ }
+
+ list.cmp = fspathcmp;
+ string_list_sort(&list);
+
+ if (list.nr) {
+ warning(_("the following paths have collided (e.g. case-sensitive paths\n"
+ "on a case-insensitive filesystem) and only one from the same\n"
+ "colliding group is in the working tree:\n"));
+
+ for (i = 0; i < list.nr; i++)
+ fprintf(stderr, " '%s'\n", list.items[i].string);
+ }
+
+ string_list_clear(&list, 0);
+}
+
static int check_updates(struct unpack_trees_options *o)
{
unsigned cnt = 0;
int errs = 0;
- struct progress *progress = NULL;
+ struct progress *progress;
struct index_state *index = &o->result;
struct checkout state = CHECKOUT_INIT;
int i;
+ trace_performance_enter();
state.force = 1;
state.quiet = 1;
state.refresh_cache = 1;
state.istate = index;
+ if (o->clone)
+ setup_collided_checkout_detection(&state, index);
+
progress = get_progress(o);
if (o->update)
errs |= finish_delayed_checkout(&state);
if (o->update)
git_attr_set_direction(GIT_ATTR_CHECKIN);
+
+ if (o->clone)
+ report_collided_checkout(index);
+
+ trace_performance_leave("check_updates");
return errs != 0;
}
static inline int are_same_oid(struct name_entry *name_j, struct name_entry *name_k)
{
- return name_j->oid && name_k->oid && !oidcmp(name_j->oid, name_k->oid);
+ return name_j->oid && name_k->oid && oideq(name_j->oid, name_k->oid);
+}
+
+static int all_trees_same_as_cache_tree(int n, unsigned long dirmask,
+ struct name_entry *names,
+ struct traverse_info *info)
+{
+ struct unpack_trees_options *o = info->data;
+ int i;
+
+ if (!o->merge || dirmask != ((1 << n) - 1))
+ return 0;
+
+ for (i = 1; i < n; i++)
+ if (!are_same_oid(names, names + i))
+ return 0;
+
+ return cache_tree_matches_traversal(o->src_index->cache_tree, names, info);
+}
+
+static int index_pos_by_traverse_info(struct name_entry *names,
+ struct traverse_info *info)
+{
+ struct unpack_trees_options *o = info->data;
+ int len = traverse_path_len(info, names);
+ char *name = xmalloc(len + 1 /* slash */ + 1 /* NUL */);
+ int pos;
+
+ make_traverse_path(name, info, names);
+ name[len++] = '/';
+ name[len] = '\0';
+ pos = index_name_pos(o->src_index, name, len);
+ if (pos >= 0)
+ BUG("This is a directory and should not exist in index");
+ pos = -pos - 1;
+ if (!starts_with(o->src_index->cache[pos]->name, name) ||
+ (pos > 0 && starts_with(o->src_index->cache[pos-1]->name, name)))
+ BUG("pos must point at the first entry in this directory");
+ free(name);
+ return pos;
+}
+
+/*
+ * Fast path if we detect that all trees are the same as cache-tree at this
+ * path. We'll walk these trees in an iterative loop using cache-tree/index
+ * instead of ODB since we already know what these trees contain.
+ */
+static int traverse_by_cache_tree(int pos, int nr_entries, int nr_names,
+ struct name_entry *names,
+ struct traverse_info *info)
+{
+ struct cache_entry *src[MAX_UNPACK_TREES + 1] = { NULL, };
+ struct unpack_trees_options *o = info->data;
+ struct cache_entry *tree_ce = NULL;
+ int ce_len = 0;
+ int i, d;
+
+ if (!o->merge)
+ BUG("We need cache-tree to do this optimization");
+
+ /*
+ * Do what unpack_callback() and unpack_nondirectories() normally
+ * do. But we walk all paths in an iterative loop instead.
+ *
+ * D/F conflicts and higher stage entries are not a concern
+ * because cache-tree would be invalidated and we would never
+ * get here in the first place.
+ */
+ for (i = 0; i < nr_entries; i++) {
+ int new_ce_len, len, rc;
+
+ src[0] = o->src_index->cache[pos + i];
+
+ len = ce_namelen(src[0]);
+ new_ce_len = cache_entry_size(len);
+
+ if (new_ce_len > ce_len) {
+ new_ce_len <<= 1;
+ tree_ce = xrealloc(tree_ce, new_ce_len);
+ memset(tree_ce, 0, new_ce_len);
+ ce_len = new_ce_len;
+
+ tree_ce->ce_flags = create_ce_flags(0);
+
+ for (d = 1; d <= nr_names; d++)
+ src[d] = tree_ce;
+ }
+
+ tree_ce->ce_mode = src[0]->ce_mode;
+ tree_ce->ce_namelen = len;
+ oidcpy(&tree_ce->oid, &src[0]->oid);
+ memcpy(tree_ce->name, src[0]->name, len + 1);
+
+ rc = call_unpack_fn((const struct cache_entry * const *)src, o);
+ if (rc < 0) {
+ free(tree_ce);
+ return rc;
+ }
+
+ mark_ce_used(src[0], o);
+ }
+ free(tree_ce);
+ if (o->debug_unpack)
+ printf("Unpacked %d entries from %s to %s using cache-tree\n",
+ nr_entries,
+ o->src_index->cache[pos]->name,
+ o->src_index->cache[pos + nr_entries - 1]->name);
+ return 0;
}
static int traverse_trees_recursive(int n, unsigned long dirmask,
void *buf[MAX_UNPACK_TREES];
struct traverse_info newinfo;
struct name_entry *p;
+ int nr_entries;
+
+ nr_entries = all_trees_same_as_cache_tree(n, dirmask, names, info);
+ if (nr_entries > 0) {
+ struct unpack_trees_options *o = info->data;
+ int pos = index_pos_by_traverse_info(names, info);
+
+ if (!o->merge || df_conflicts)
+ BUG("Wrong condition to get here buddy");
+
+ /*
+ * All entries up to 'pos' must have been processed
+ * (i.e. marked CE_UNPACKED) at this point. But to be safe,
+ * save and restore cache_bottom anyway to not miss
+ * unprocessed entries before 'pos'.
+ */
+ bottom = o->cache_bottom;
+ ret = traverse_by_cache_tree(pos, nr_entries, n, names, info);
+ o->cache_bottom = bottom;
+ return ret;
+ }
p = names;
while (!p->mode)
return ce;
}
+/*
+ * Note that traverse_by_cache_tree() duplicates some logic in this function
+ * without actually calling it. If you change the logic here you may need to
+ * check and change there as well.
+ */
static int unpack_nondirectories(int n, unsigned long mask,
unsigned long dirmask,
struct cache_entry **src,
debug_name_entry(i, names + i);
}
+/*
+ * Note that traverse_by_cache_tree() duplicates some logic in this function
+ * without actually calling it. If you change the logic here you may need to
+ * check and change there as well.
+ */
static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, struct name_entry *names, struct traverse_info *info)
{
struct cache_entry *src[MAX_UNPACK_TREES + 1] = { NULL, };
if (len > MAX_UNPACK_TREES)
die("unpack_trees takes at most %d trees", MAX_UNPACK_TREES);
+ trace_performance_enter();
memset(&el, 0, sizeof(el));
if (!core_apply_sparse_checkout || !o->update)
o->skip_sparse_checkout = 1;
}
}
- if (traverse_trees(len, t, &info) < 0)
+ trace_performance_enter();
+ ret = traverse_trees(len, t, &info);
+ trace_performance_leave("traverse_trees");
+ if (ret < 0)
goto return_failed;
}
ret = check_updates(o) ? (-2) : 0;
if (o->dst_index) {
+ move_index_extensions(&o->result, o->src_index);
if (!ret) {
+ if (git_env_bool("GIT_TEST_CHECK_CACHE_TREE", 0))
+ cache_tree_verify(&o->result);
if (!o->result.cache_tree)
o->result.cache_tree = cache_tree();
if (!cache_tree_fully_valid(o->result.cache_tree))
WRITE_TREE_SILENT |
WRITE_TREE_REPAIR);
}
- move_index_extensions(&o->result, o->src_index);
discard_index(o->dst_index);
*o->dst_index = o->result;
} else {
o->src_index = NULL;
done:
+ trace_performance_leave("unpack_trees");
clear_exclude_list(&el);
return ret;
if ((a->ce_flags | b->ce_flags) & CE_CONFLICTED)
return 0;
return a->ce_mode == b->ce_mode &&
- !oidcmp(&a->oid, &b->oid);
+ oideq(&a->oid, &b->oid);
}
* If we are not going to update the submodule, then
* we don't care.
*/
- if (!sub_head && !oidcmp(&oid, &ce->oid))
+ if (!sub_head && oideq(&oid, &ce->oid))
return 0;
return verify_clean_submodule(sub_head ? NULL : oid_to_hex(&oid),
ce, error_type, o);
if (verify_uptodate(ce2, o))
return -1;
add_entry(o, ce2, CE_REMOVE, 0);
+ invalidate_ce_path(ce, o);
mark_ce_used(ce2, o);
}
cnt++;
invalidate_ce_path(old, o);
}
- do_add_entry(o, merge, update, CE_STAGEMASK);
+ if (do_add_entry(o, merge, update, CE_STAGEMASK) < 0)
+ return -1;
return 1;
}
struct unpack_trees_options *o)
{
add_entry(o, ce, 0, 0);
+ if (ce_stage(ce))
+ invalidate_ce_path(ce, o);
return 1;
}