diff options
Diffstat (limited to 'refs')
| -rw-r--r-- | refs/debug.c | 473 | ||||
| -rw-r--r-- | refs/files-backend.c | 3303 | ||||
| -rw-r--r-- | refs/iterator.c | 435 | ||||
| -rw-r--r-- | refs/packed-backend.c | 1615 | ||||
| -rw-r--r-- | refs/packed-backend.h | 39 | ||||
| -rw-r--r-- | refs/ref-cache.c | 504 | ||||
| -rw-r--r-- | refs/ref-cache.h | 220 | ||||
| -rw-r--r-- | refs/refs-internal.h | 737 |
8 files changed, 7326 insertions, 0 deletions
diff --git a/refs/debug.c b/refs/debug.c new file mode 100644 index 0000000..eed8bc9 --- /dev/null +++ b/refs/debug.c @@ -0,0 +1,473 @@ + +#include "refs-internal.h" +#include "trace.h" + +static struct trace_key trace_refs = TRACE_KEY_INIT(REFS); + +struct debug_ref_store { + struct ref_store base; + struct ref_store *refs; +}; + +extern struct ref_storage_be refs_be_debug; + +struct ref_store *maybe_debug_wrap_ref_store(const char *gitdir, struct ref_store *store) +{ + struct debug_ref_store *res; + struct ref_storage_be *be_copy; + + if (!trace_want(&trace_refs)) { + return store; + } + res = xmalloc(sizeof(struct debug_ref_store)); + be_copy = xmalloc(sizeof(*be_copy)); + *be_copy = refs_be_debug; + /* we never deallocate backends, so safe to copy the pointer. */ + be_copy->name = store->be->name; + trace_printf_key(&trace_refs, "ref_store for %s\n", gitdir); + res->refs = store; + base_ref_store_init((struct ref_store *)res, store->repo, gitdir, + be_copy); + return (struct ref_store *)res; +} + +static int debug_init_db(struct ref_store *refs, struct strbuf *err) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)refs; + int res = drefs->refs->be->init_db(drefs->refs, err); + trace_printf_key(&trace_refs, "init_db: %d\n", res); + return res; +} + +static int debug_transaction_prepare(struct ref_store *refs, + struct ref_transaction *transaction, + struct strbuf *err) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)refs; + int res; + transaction->ref_store = drefs->refs; + res = drefs->refs->be->transaction_prepare(drefs->refs, transaction, + err); + trace_printf_key(&trace_refs, "transaction_prepare: %d \"%s\"\n", res, + err->buf); + return res; +} + +static void print_update(int i, const char *refname, + const struct object_id *old_oid, + const struct object_id *new_oid, unsigned int flags, + unsigned int type, const char *msg) +{ + char o[GIT_MAX_HEXSZ + 1] = "null"; + char n[GIT_MAX_HEXSZ + 1] = "null"; + if (old_oid) + oid_to_hex_r(o, old_oid); + if (new_oid) + oid_to_hex_r(n, new_oid); + + type &= 0xf; /* see refs.h REF_* */ + flags &= REF_HAVE_NEW | REF_HAVE_OLD | REF_NO_DEREF | + REF_FORCE_CREATE_REFLOG; + trace_printf_key(&trace_refs, "%d: %s %s -> %s (F=0x%x, T=0x%x) \"%s\"\n", i, refname, + o, n, flags, type, msg); +} + +static void print_transaction(struct ref_transaction *transaction) +{ + int i; + trace_printf_key(&trace_refs, "transaction {\n"); + for (i = 0; i < transaction->nr; i++) { + struct ref_update *u = transaction->updates[i]; + print_update(i, u->refname, &u->old_oid, &u->new_oid, u->flags, + u->type, u->msg); + } + trace_printf_key(&trace_refs, "}\n"); +} + +static int debug_transaction_finish(struct ref_store *refs, + struct ref_transaction *transaction, + struct strbuf *err) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)refs; + int res; + transaction->ref_store = drefs->refs; + res = drefs->refs->be->transaction_finish(drefs->refs, transaction, + err); + print_transaction(transaction); + trace_printf_key(&trace_refs, "finish: %d\n", res); + return res; +} + +static int debug_transaction_abort(struct ref_store *refs, + struct ref_transaction *transaction, + struct strbuf *err) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)refs; + int res; + transaction->ref_store = drefs->refs; + res = drefs->refs->be->transaction_abort(drefs->refs, transaction, err); + return res; +} + +static int debug_initial_transaction_commit(struct ref_store *refs, + struct ref_transaction *transaction, + struct strbuf *err) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)refs; + int res; + transaction->ref_store = drefs->refs; + res = drefs->refs->be->initial_transaction_commit(drefs->refs, + transaction, err); + return res; +} + +static int debug_pack_refs(struct ref_store *ref_store, unsigned int flags) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + int res = drefs->refs->be->pack_refs(drefs->refs, flags); + trace_printf_key(&trace_refs, "pack_refs: %d\n", res); + return res; +} + +static int debug_create_symref(struct ref_store *ref_store, + const char *ref_name, const char *target, + const char *logmsg) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + int res = drefs->refs->be->create_symref(drefs->refs, ref_name, target, + logmsg); + trace_printf_key(&trace_refs, "create_symref: %s -> %s \"%s\": %d\n", ref_name, + target, logmsg, res); + return res; +} + +static int debug_delete_refs(struct ref_store *ref_store, const char *msg, + struct string_list *refnames, unsigned int flags) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + int res = + drefs->refs->be->delete_refs(drefs->refs, msg, refnames, flags); + int i; + trace_printf_key(&trace_refs, "delete_refs {\n"); + for (i = 0; i < refnames->nr; i++) + trace_printf_key(&trace_refs, "%s\n", refnames->items[i].string); + trace_printf_key(&trace_refs, "}: %d\n", res); + return res; +} + +static int debug_rename_ref(struct ref_store *ref_store, const char *oldref, + const char *newref, const char *logmsg) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + int res = drefs->refs->be->rename_ref(drefs->refs, oldref, newref, + logmsg); + trace_printf_key(&trace_refs, "rename_ref: %s -> %s \"%s\": %d\n", oldref, newref, + logmsg, res); + return res; +} + +static int debug_copy_ref(struct ref_store *ref_store, const char *oldref, + const char *newref, const char *logmsg) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + int res = + drefs->refs->be->copy_ref(drefs->refs, oldref, newref, logmsg); + trace_printf_key(&trace_refs, "copy_ref: %s -> %s \"%s\": %d\n", oldref, newref, + logmsg, res); + return res; +} + +struct debug_ref_iterator { + struct ref_iterator base; + struct ref_iterator *iter; +}; + +static int debug_ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + struct debug_ref_iterator *diter = + (struct debug_ref_iterator *)ref_iterator; + int res = diter->iter->vtable->advance(diter->iter); + if (res) + trace_printf_key(&trace_refs, "iterator_advance: (%d)\n", res); + else + trace_printf_key(&trace_refs, "iterator_advance: %s (0)\n", + diter->iter->refname); + + diter->base.ordered = diter->iter->ordered; + diter->base.refname = diter->iter->refname; + diter->base.oid = diter->iter->oid; + diter->base.flags = diter->iter->flags; + return res; +} + +static int debug_ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) +{ + struct debug_ref_iterator *diter = + (struct debug_ref_iterator *)ref_iterator; + int res = diter->iter->vtable->peel(diter->iter, peeled); + trace_printf_key(&trace_refs, "iterator_peel: %s: %d\n", diter->iter->refname, res); + return res; +} + +static int debug_ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + struct debug_ref_iterator *diter = + (struct debug_ref_iterator *)ref_iterator; + int res = diter->iter->vtable->abort(diter->iter); + trace_printf_key(&trace_refs, "iterator_abort: %d\n", res); + return res; +} + +static struct ref_iterator_vtable debug_ref_iterator_vtable = { + .advance = debug_ref_iterator_advance, + .peel = debug_ref_iterator_peel, + .abort = debug_ref_iterator_abort, +}; + +static struct ref_iterator * +debug_ref_iterator_begin(struct ref_store *ref_store, const char *prefix, + unsigned int flags) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + struct ref_iterator *res = + drefs->refs->be->iterator_begin(drefs->refs, prefix, flags); + struct debug_ref_iterator *diter = xcalloc(1, sizeof(*diter)); + base_ref_iterator_init(&diter->base, &debug_ref_iterator_vtable, 1); + diter->iter = res; + trace_printf_key(&trace_refs, "ref_iterator_begin: \"%s\" (0x%x)\n", + prefix, flags); + return &diter->base; +} + +static int debug_read_raw_ref(struct ref_store *ref_store, const char *refname, + struct object_id *oid, struct strbuf *referent, + unsigned int *type, int *failure_errno) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + int res = 0; + + oidcpy(oid, null_oid()); + res = drefs->refs->be->read_raw_ref(drefs->refs, refname, oid, referent, + type, failure_errno); + + if (res == 0) { + trace_printf_key(&trace_refs, "read_raw_ref: %s: %s (=> %s) type %x: %d\n", + refname, oid_to_hex(oid), referent->buf, *type, res); + } else { + trace_printf_key(&trace_refs, + "read_raw_ref: %s: %d (errno %d)\n", refname, + res, *failure_errno); + } + return res; +} + +static int debug_read_symbolic_ref(struct ref_store *ref_store, const char *refname, + struct strbuf *referent) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + struct ref_store *refs = drefs->refs; + int res; + + res = refs->be->read_symbolic_ref(refs, refname, referent); + if (!res) + trace_printf_key(&trace_refs, "read_symbolic_ref: %s: (%s)\n", + refname, referent->buf); + else + trace_printf_key(&trace_refs, + "read_symbolic_ref: %s: %d\n", refname, res); + return res; + +} + +static struct ref_iterator * +debug_reflog_iterator_begin(struct ref_store *ref_store) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + struct ref_iterator *res = + drefs->refs->be->reflog_iterator_begin(drefs->refs); + trace_printf_key(&trace_refs, "for_each_reflog_iterator_begin\n"); + return res; +} + +struct debug_reflog { + const char *refname; + each_reflog_ent_fn *fn; + void *cb_data; +}; + +static int debug_print_reflog_ent(struct object_id *old_oid, + struct object_id *new_oid, + const char *committer, timestamp_t timestamp, + int tz, const char *msg, void *cb_data) +{ + struct debug_reflog *dbg = (struct debug_reflog *)cb_data; + int ret; + char o[GIT_MAX_HEXSZ + 1] = "null"; + char n[GIT_MAX_HEXSZ + 1] = "null"; + char *msgend = strchrnul(msg, '\n'); + if (old_oid) + oid_to_hex_r(o, old_oid); + if (new_oid) + oid_to_hex_r(n, new_oid); + + ret = dbg->fn(old_oid, new_oid, committer, timestamp, tz, msg, + dbg->cb_data); + trace_printf_key(&trace_refs, + "reflog_ent %s (ret %d): %s -> %s, %s %ld \"%.*s\"\n", + dbg->refname, ret, o, n, committer, + (long int)timestamp, (int)(msgend - msg), msg); + return ret; +} + +static int debug_for_each_reflog_ent(struct ref_store *ref_store, + const char *refname, each_reflog_ent_fn fn, + void *cb_data) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + struct debug_reflog dbg = { + .refname = refname, + .fn = fn, + .cb_data = cb_data, + }; + + int res = drefs->refs->be->for_each_reflog_ent( + drefs->refs, refname, &debug_print_reflog_ent, &dbg); + trace_printf_key(&trace_refs, "for_each_reflog: %s: %d\n", refname, res); + return res; +} + +static int debug_for_each_reflog_ent_reverse(struct ref_store *ref_store, + const char *refname, + each_reflog_ent_fn fn, + void *cb_data) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + struct debug_reflog dbg = { + .refname = refname, + .fn = fn, + .cb_data = cb_data, + }; + int res = drefs->refs->be->for_each_reflog_ent_reverse( + drefs->refs, refname, &debug_print_reflog_ent, &dbg); + trace_printf_key(&trace_refs, "for_each_reflog_reverse: %s: %d\n", refname, res); + return res; +} + +static int debug_reflog_exists(struct ref_store *ref_store, const char *refname) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + int res = drefs->refs->be->reflog_exists(drefs->refs, refname); + trace_printf_key(&trace_refs, "reflog_exists: %s: %d\n", refname, res); + return res; +} + +static int debug_create_reflog(struct ref_store *ref_store, const char *refname, + struct strbuf *err) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + int res = drefs->refs->be->create_reflog(drefs->refs, refname, err); + trace_printf_key(&trace_refs, "create_reflog: %s: %d\n", refname, res); + return res; +} + +static int debug_delete_reflog(struct ref_store *ref_store, const char *refname) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + int res = drefs->refs->be->delete_reflog(drefs->refs, refname); + trace_printf_key(&trace_refs, "delete_reflog: %s: %d\n", refname, res); + return res; +} + +struct debug_reflog_expiry_should_prune { + reflog_expiry_prepare_fn *prepare; + reflog_expiry_should_prune_fn *should_prune; + reflog_expiry_cleanup_fn *cleanup; + void *cb_data; +}; + +static void debug_reflog_expiry_prepare(const char *refname, + const struct object_id *oid, + void *cb_data) +{ + struct debug_reflog_expiry_should_prune *prune = cb_data; + trace_printf_key(&trace_refs, "reflog_expire_prepare: %s\n", refname); + prune->prepare(refname, oid, prune->cb_data); +} + +static int debug_reflog_expiry_should_prune_fn(struct object_id *ooid, + struct object_id *noid, + const char *email, + timestamp_t timestamp, int tz, + const char *message, void *cb_data) { + struct debug_reflog_expiry_should_prune *prune = cb_data; + + int result = prune->should_prune(ooid, noid, email, timestamp, tz, message, prune->cb_data); + trace_printf_key(&trace_refs, "reflog_expire_should_prune: %s %ld: %d\n", message, (long int) timestamp, result); + return result; +} + +static void debug_reflog_expiry_cleanup(void *cb_data) +{ + struct debug_reflog_expiry_should_prune *prune = cb_data; + prune->cleanup(prune->cb_data); +} + +static int debug_reflog_expire(struct ref_store *ref_store, const char *refname, + unsigned int flags, + reflog_expiry_prepare_fn prepare_fn, + reflog_expiry_should_prune_fn should_prune_fn, + reflog_expiry_cleanup_fn cleanup_fn, + void *policy_cb_data) +{ + struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store; + struct debug_reflog_expiry_should_prune prune = { + .prepare = prepare_fn, + .cleanup = cleanup_fn, + .should_prune = should_prune_fn, + .cb_data = policy_cb_data, + }; + int res = drefs->refs->be->reflog_expire(drefs->refs, refname, + flags, &debug_reflog_expiry_prepare, + &debug_reflog_expiry_should_prune_fn, + &debug_reflog_expiry_cleanup, + &prune); + trace_printf_key(&trace_refs, "reflog_expire: %s: %d\n", refname, res); + return res; +} + +struct ref_storage_be refs_be_debug = { + .next = NULL, + .name = "debug", + .init = NULL, + .init_db = debug_init_db, + + /* + * None of these should be NULL. If the "files" backend (in + * "struct ref_storage_be refs_be_files" in files-backend.c) + * has a function we should also have a wrapper for it here. + * Test the output with "GIT_TRACE_REFS=1". + */ + .transaction_prepare = debug_transaction_prepare, + .transaction_finish = debug_transaction_finish, + .transaction_abort = debug_transaction_abort, + .initial_transaction_commit = debug_initial_transaction_commit, + + .pack_refs = debug_pack_refs, + .create_symref = debug_create_symref, + .delete_refs = debug_delete_refs, + .rename_ref = debug_rename_ref, + .copy_ref = debug_copy_ref, + + .iterator_begin = debug_ref_iterator_begin, + .read_raw_ref = debug_read_raw_ref, + .read_symbolic_ref = debug_read_symbolic_ref, + + .reflog_iterator_begin = debug_reflog_iterator_begin, + .for_each_reflog_ent = debug_for_each_reflog_ent, + .for_each_reflog_ent_reverse = debug_for_each_reflog_ent_reverse, + .reflog_exists = debug_reflog_exists, + .create_reflog = debug_create_reflog, + .delete_reflog = debug_delete_reflog, + .reflog_expire = debug_reflog_expire, +}; diff --git a/refs/files-backend.c b/refs/files-backend.c new file mode 100644 index 0000000..b899543 --- /dev/null +++ b/refs/files-backend.c @@ -0,0 +1,3303 @@ +#include "../cache.h" +#include "../config.h" +#include "../refs.h" +#include "refs-internal.h" +#include "ref-cache.h" +#include "packed-backend.h" +#include "../iterator.h" +#include "../dir-iterator.h" +#include "../lockfile.h" +#include "../object.h" +#include "../dir.h" +#include "../chdir-notify.h" +#include "worktree.h" + +/* + * This backend uses the following flags in `ref_update::flags` for + * internal bookkeeping purposes. Their numerical values must not + * conflict with REF_NO_DEREF, REF_FORCE_CREATE_REFLOG, REF_HAVE_NEW, + * or REF_HAVE_OLD, which are also stored in `ref_update::flags`. + */ + +/* + * Used as a flag in ref_update::flags when a loose ref is being + * pruned. This flag must only be used when REF_NO_DEREF is set. + */ +#define REF_IS_PRUNING (1 << 4) + +/* + * Flag passed to lock_ref_sha1_basic() telling it to tolerate broken + * refs (i.e., because the reference is about to be deleted anyway). + */ +#define REF_DELETING (1 << 5) + +/* + * Used as a flag in ref_update::flags when the lockfile needs to be + * committed. + */ +#define REF_NEEDS_COMMIT (1 << 6) + +/* + * Used as a flag in ref_update::flags when the ref_update was via an + * update to HEAD. + */ +#define REF_UPDATE_VIA_HEAD (1 << 8) + +/* + * Used as a flag in ref_update::flags when a reference has been + * deleted and the ref's parent directories may need cleanup. + */ +#define REF_DELETED_RMDIR (1 << 9) + +struct ref_lock { + char *ref_name; + struct lock_file lk; + struct object_id old_oid; +}; + +struct files_ref_store { + struct ref_store base; + unsigned int store_flags; + + char *gitcommondir; + + struct ref_cache *loose; + + struct ref_store *packed_ref_store; +}; + +static void clear_loose_ref_cache(struct files_ref_store *refs) +{ + if (refs->loose) { + free_ref_cache(refs->loose); + refs->loose = NULL; + } +} + +/* + * Create a new submodule ref cache and add it to the internal + * set of caches. + */ +static struct ref_store *files_ref_store_create(struct repository *repo, + const char *gitdir, + unsigned int flags) +{ + struct files_ref_store *refs = xcalloc(1, sizeof(*refs)); + struct ref_store *ref_store = (struct ref_store *)refs; + struct strbuf sb = STRBUF_INIT; + + base_ref_store_init(ref_store, repo, gitdir, &refs_be_files); + refs->store_flags = flags; + get_common_dir_noenv(&sb, gitdir); + refs->gitcommondir = strbuf_detach(&sb, NULL); + refs->packed_ref_store = + packed_ref_store_create(repo, refs->gitcommondir, flags); + + chdir_notify_reparent("files-backend $GIT_DIR", &refs->base.gitdir); + chdir_notify_reparent("files-backend $GIT_COMMONDIR", + &refs->gitcommondir); + + return ref_store; +} + +/* + * Die if refs is not the main ref store. caller is used in any + * necessary error messages. + */ +static void files_assert_main_repository(struct files_ref_store *refs, + const char *caller) +{ + if (refs->store_flags & REF_STORE_MAIN) + return; + + BUG("operation %s only allowed for main ref store", caller); +} + +/* + * Downcast ref_store to files_ref_store. Die if ref_store is not a + * files_ref_store. required_flags is compared with ref_store's + * store_flags to ensure the ref_store has all required capabilities. + * "caller" is used in any necessary error messages. + */ +static struct files_ref_store *files_downcast(struct ref_store *ref_store, + unsigned int required_flags, + const char *caller) +{ + struct files_ref_store *refs; + + if (ref_store->be != &refs_be_files) + BUG("ref_store is type \"%s\" not \"files\" in %s", + ref_store->be->name, caller); + + refs = (struct files_ref_store *)ref_store; + + if ((refs->store_flags & required_flags) != required_flags) + BUG("operation %s requires abilities 0x%x, but only have 0x%x", + caller, required_flags, refs->store_flags); + + return refs; +} + +static void files_reflog_path(struct files_ref_store *refs, + struct strbuf *sb, + const char *refname) +{ + const char *bare_refname; + const char *wtname; + int wtname_len; + enum ref_worktree_type wt_type = parse_worktree_ref( + refname, &wtname, &wtname_len, &bare_refname); + + switch (wt_type) { + case REF_WORKTREE_CURRENT: + strbuf_addf(sb, "%s/logs/%s", refs->base.gitdir, refname); + break; + case REF_WORKTREE_SHARED: + case REF_WORKTREE_MAIN: + strbuf_addf(sb, "%s/logs/%s", refs->gitcommondir, bare_refname); + break; + case REF_WORKTREE_OTHER: + strbuf_addf(sb, "%s/worktrees/%.*s/logs/%s", refs->gitcommondir, + wtname_len, wtname, bare_refname); + break; + default: + BUG("unknown ref type %d of ref %s", wt_type, refname); + } +} + +static void files_ref_path(struct files_ref_store *refs, + struct strbuf *sb, + const char *refname) +{ + const char *bare_refname; + const char *wtname; + int wtname_len; + enum ref_worktree_type wt_type = parse_worktree_ref( + refname, &wtname, &wtname_len, &bare_refname); + switch (wt_type) { + case REF_WORKTREE_CURRENT: + strbuf_addf(sb, "%s/%s", refs->base.gitdir, refname); + break; + case REF_WORKTREE_OTHER: + strbuf_addf(sb, "%s/worktrees/%.*s/%s", refs->gitcommondir, + wtname_len, wtname, bare_refname); + break; + case REF_WORKTREE_SHARED: + case REF_WORKTREE_MAIN: + strbuf_addf(sb, "%s/%s", refs->gitcommondir, bare_refname); + break; + default: + BUG("unknown ref type %d of ref %s", wt_type, refname); + } +} + +/* + * Manually add refs/bisect, refs/rewritten and refs/worktree, which, being + * per-worktree, might not appear in the directory listing for + * refs/ in the main repo. + */ +static void add_per_worktree_entries_to_dir(struct ref_dir *dir, const char *dirname) +{ + const char *prefixes[] = { "refs/bisect/", "refs/worktree/", "refs/rewritten/" }; + int ip; + + if (strcmp(dirname, "refs/")) + return; + + for (ip = 0; ip < ARRAY_SIZE(prefixes); ip++) { + const char *prefix = prefixes[ip]; + int prefix_len = strlen(prefix); + struct ref_entry *child_entry; + int pos; + + pos = search_ref_dir(dir, prefix, prefix_len); + if (pos >= 0) + continue; + child_entry = create_dir_entry(dir->cache, prefix, prefix_len); + add_entry_to_dir(dir, child_entry); + } +} + +/* + * Read the loose references from the namespace dirname into dir + * (without recursing). dirname must end with '/'. dir must be the + * directory entry corresponding to dirname. + */ +static void loose_fill_ref_dir(struct ref_store *ref_store, + struct ref_dir *dir, const char *dirname) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_READ, "fill_ref_dir"); + DIR *d; + struct dirent *de; + int dirnamelen = strlen(dirname); + struct strbuf refname; + struct strbuf path = STRBUF_INIT; + size_t path_baselen; + + files_ref_path(refs, &path, dirname); + path_baselen = path.len; + + d = opendir(path.buf); + if (!d) { + strbuf_release(&path); + return; + } + + strbuf_init(&refname, dirnamelen + 257); + strbuf_add(&refname, dirname, dirnamelen); + + while ((de = readdir(d)) != NULL) { + struct object_id oid; + struct stat st; + int flag; + + if (de->d_name[0] == '.') + continue; + if (ends_with(de->d_name, ".lock")) + continue; + strbuf_addstr(&refname, de->d_name); + strbuf_addstr(&path, de->d_name); + if (stat(path.buf, &st) < 0) { + ; /* silently ignore */ + } else if (S_ISDIR(st.st_mode)) { + strbuf_addch(&refname, '/'); + add_entry_to_dir(dir, + create_dir_entry(dir->cache, refname.buf, + refname.len)); + } else { + if (!refs_resolve_ref_unsafe(&refs->base, + refname.buf, + RESOLVE_REF_READING, + &oid, &flag)) { + oidclr(&oid); + flag |= REF_ISBROKEN; + } else if (is_null_oid(&oid)) { + /* + * It is so astronomically unlikely + * that null_oid is the OID of an + * actual object that we consider its + * appearance in a loose reference + * file to be repo corruption + * (probably due to a software bug). + */ + flag |= REF_ISBROKEN; + } + + if (check_refname_format(refname.buf, + REFNAME_ALLOW_ONELEVEL)) { + if (!refname_is_safe(refname.buf)) + die("loose refname is dangerous: %s", refname.buf); + oidclr(&oid); + flag |= REF_BAD_NAME | REF_ISBROKEN; + } + add_entry_to_dir(dir, + create_ref_entry(refname.buf, &oid, flag)); + } + strbuf_setlen(&refname, dirnamelen); + strbuf_setlen(&path, path_baselen); + } + strbuf_release(&refname); + strbuf_release(&path); + closedir(d); + + add_per_worktree_entries_to_dir(dir, dirname); +} + +static struct ref_cache *get_loose_ref_cache(struct files_ref_store *refs) +{ + if (!refs->loose) { + /* + * Mark the top-level directory complete because we + * are about to read the only subdirectory that can + * hold references: + */ + refs->loose = create_ref_cache(&refs->base, loose_fill_ref_dir); + + /* We're going to fill the top level ourselves: */ + refs->loose->root->flag &= ~REF_INCOMPLETE; + + /* + * Add an incomplete entry for "refs/" (to be filled + * lazily): + */ + add_entry_to_dir(get_ref_dir(refs->loose->root), + create_dir_entry(refs->loose, "refs/", 5)); + } + return refs->loose; +} + +static int read_ref_internal(struct ref_store *ref_store, const char *refname, + struct object_id *oid, struct strbuf *referent, + unsigned int *type, int *failure_errno, int skip_packed_refs) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_READ, "read_raw_ref"); + struct strbuf sb_contents = STRBUF_INIT; + struct strbuf sb_path = STRBUF_INIT; + const char *path; + const char *buf; + struct stat st; + int fd; + int ret = -1; + int remaining_retries = 3; + int myerr = 0; + + *type = 0; + strbuf_reset(&sb_path); + + files_ref_path(refs, &sb_path, refname); + + path = sb_path.buf; + +stat_ref: + /* + * We might have to loop back here to avoid a race + * condition: first we lstat() the file, then we try + * to read it as a link or as a file. But if somebody + * changes the type of the file (file <-> directory + * <-> symlink) between the lstat() and reading, then + * we don't want to report that as an error but rather + * try again starting with the lstat(). + * + * We'll keep a count of the retries, though, just to avoid + * any confusing situation sending us into an infinite loop. + */ + + if (remaining_retries-- <= 0) + goto out; + + if (lstat(path, &st) < 0) { + int ignore_errno; + myerr = errno; + if (myerr != ENOENT || skip_packed_refs) + goto out; + if (refs_read_raw_ref(refs->packed_ref_store, refname, oid, + referent, type, &ignore_errno)) { + myerr = ENOENT; + goto out; + } + ret = 0; + goto out; + } + + /* Follow "normalized" - ie "refs/.." symlinks by hand */ + if (S_ISLNK(st.st_mode)) { + strbuf_reset(&sb_contents); + if (strbuf_readlink(&sb_contents, path, st.st_size) < 0) { + myerr = errno; + if (myerr == ENOENT || myerr == EINVAL) + /* inconsistent with lstat; retry */ + goto stat_ref; + else + goto out; + } + if (starts_with(sb_contents.buf, "refs/") && + !check_refname_format(sb_contents.buf, 0)) { + strbuf_swap(&sb_contents, referent); + *type |= REF_ISSYMREF; + ret = 0; + goto out; + } + /* + * It doesn't look like a refname; fall through to just + * treating it like a non-symlink, and reading whatever it + * points to. + */ + } + + /* Is it a directory? */ + if (S_ISDIR(st.st_mode)) { + int ignore_errno; + /* + * Even though there is a directory where the loose + * ref is supposed to be, there could still be a + * packed ref: + */ + if (skip_packed_refs || + refs_read_raw_ref(refs->packed_ref_store, refname, oid, + referent, type, &ignore_errno)) { + myerr = EISDIR; + goto out; + } + ret = 0; + goto out; + } + + /* + * Anything else, just open it and try to use it as + * a ref + */ + fd = open(path, O_RDONLY); + if (fd < 0) { + myerr = errno; + if (myerr == ENOENT && !S_ISLNK(st.st_mode)) + /* inconsistent with lstat; retry */ + goto stat_ref; + else + goto out; + } + strbuf_reset(&sb_contents); + if (strbuf_read(&sb_contents, fd, 256) < 0) { + myerr = errno; + close(fd); + goto out; + } + close(fd); + strbuf_rtrim(&sb_contents); + buf = sb_contents.buf; + + ret = parse_loose_ref_contents(buf, oid, referent, type, &myerr); + +out: + if (ret && !myerr) + BUG("returning non-zero %d, should have set myerr!", ret); + *failure_errno = myerr; + + strbuf_release(&sb_path); + strbuf_release(&sb_contents); + errno = 0; + return ret; +} + +static int files_read_raw_ref(struct ref_store *ref_store, const char *refname, + struct object_id *oid, struct strbuf *referent, + unsigned int *type, int *failure_errno) +{ + return read_ref_internal(ref_store, refname, oid, referent, type, failure_errno, 0); +} + +static int files_read_symbolic_ref(struct ref_store *ref_store, const char *refname, + struct strbuf *referent) +{ + struct object_id oid; + int failure_errno, ret; + unsigned int type; + + ret = read_ref_internal(ref_store, refname, &oid, referent, &type, &failure_errno, 1); + if (ret) + return ret; + + return !(type & REF_ISSYMREF); +} + +int parse_loose_ref_contents(const char *buf, struct object_id *oid, + struct strbuf *referent, unsigned int *type, + int *failure_errno) +{ + const char *p; + if (skip_prefix(buf, "ref:", &buf)) { + while (isspace(*buf)) + buf++; + + strbuf_reset(referent); + strbuf_addstr(referent, buf); + *type |= REF_ISSYMREF; + return 0; + } + + /* + * FETCH_HEAD has additional data after the sha. + */ + if (parse_oid_hex(buf, oid, &p) || + (*p != '\0' && !isspace(*p))) { + *type |= REF_ISBROKEN; + *failure_errno = EINVAL; + return -1; + } + return 0; +} + +static void unlock_ref(struct ref_lock *lock) +{ + rollback_lock_file(&lock->lk); + free(lock->ref_name); + free(lock); +} + +/* + * Lock refname, without following symrefs, and set *lock_p to point + * at a newly-allocated lock object. Fill in lock->old_oid, referent, + * and type similarly to read_raw_ref(). + * + * The caller must verify that refname is a "safe" reference name (in + * the sense of refname_is_safe()) before calling this function. + * + * If the reference doesn't already exist, verify that refname doesn't + * have a D/F conflict with any existing references. extras and skip + * are passed to refs_verify_refname_available() for this check. + * + * If mustexist is not set and the reference is not found or is + * broken, lock the reference anyway but clear old_oid. + * + * Return 0 on success. On failure, write an error message to err and + * return TRANSACTION_NAME_CONFLICT or TRANSACTION_GENERIC_ERROR. + * + * Implementation note: This function is basically + * + * lock reference + * read_raw_ref() + * + * but it includes a lot more code to + * - Deal with possible races with other processes + * - Avoid calling refs_verify_refname_available() when it can be + * avoided, namely if we were successfully able to read the ref + * - Generate informative error messages in the case of failure + */ +static int lock_raw_ref(struct files_ref_store *refs, + const char *refname, int mustexist, + const struct string_list *extras, + struct ref_lock **lock_p, + struct strbuf *referent, + unsigned int *type, + struct strbuf *err) +{ + struct ref_lock *lock; + struct strbuf ref_file = STRBUF_INIT; + int attempts_remaining = 3; + int ret = TRANSACTION_GENERIC_ERROR; + int failure_errno; + + assert(err); + files_assert_main_repository(refs, "lock_raw_ref"); + + *type = 0; + + /* First lock the file so it can't change out from under us. */ + + *lock_p = CALLOC_ARRAY(lock, 1); + + lock->ref_name = xstrdup(refname); + files_ref_path(refs, &ref_file, refname); + +retry: + switch (safe_create_leading_directories(ref_file.buf)) { + case SCLD_OK: + break; /* success */ + case SCLD_EXISTS: + /* + * Suppose refname is "refs/foo/bar". We just failed + * to create the containing directory, "refs/foo", + * because there was a non-directory in the way. This + * indicates a D/F conflict, probably because of + * another reference such as "refs/foo". There is no + * reason to expect this error to be transitory. + */ + if (refs_verify_refname_available(&refs->base, refname, + extras, NULL, err)) { + if (mustexist) { + /* + * To the user the relevant error is + * that the "mustexist" reference is + * missing: + */ + strbuf_reset(err); + strbuf_addf(err, "unable to resolve reference '%s'", + refname); + } else { + /* + * The error message set by + * refs_verify_refname_available() is + * OK. + */ + ret = TRANSACTION_NAME_CONFLICT; + } + } else { + /* + * The file that is in the way isn't a loose + * reference. Report it as a low-level + * failure. + */ + strbuf_addf(err, "unable to create lock file %s.lock; " + "non-directory in the way", + ref_file.buf); + } + goto error_return; + case SCLD_VANISHED: + /* Maybe another process was tidying up. Try again. */ + if (--attempts_remaining > 0) + goto retry; + /* fall through */ + default: + strbuf_addf(err, "unable to create directory for %s", + ref_file.buf); + goto error_return; + } + + if (hold_lock_file_for_update_timeout( + &lock->lk, ref_file.buf, LOCK_NO_DEREF, + get_files_ref_lock_timeout_ms()) < 0) { + int myerr = errno; + errno = 0; + if (myerr == ENOENT && --attempts_remaining > 0) { + /* + * Maybe somebody just deleted one of the + * directories leading to ref_file. Try + * again: + */ + goto retry; + } else { + unable_to_lock_message(ref_file.buf, myerr, err); + goto error_return; + } + } + + /* + * Now we hold the lock and can read the reference without + * fear that its value will change. + */ + + if (files_read_raw_ref(&refs->base, refname, &lock->old_oid, referent, + type, &failure_errno)) { + if (failure_errno == ENOENT) { + if (mustexist) { + /* Garden variety missing reference. */ + strbuf_addf(err, "unable to resolve reference '%s'", + refname); + goto error_return; + } else { + /* + * Reference is missing, but that's OK. We + * know that there is not a conflict with + * another loose reference because + * (supposing that we are trying to lock + * reference "refs/foo/bar"): + * + * - We were successfully able to create + * the lockfile refs/foo/bar.lock, so we + * know there cannot be a loose reference + * named "refs/foo". + * + * - We got ENOENT and not EISDIR, so we + * know that there cannot be a loose + * reference named "refs/foo/bar/baz". + */ + } + } else if (failure_errno == EISDIR) { + /* + * There is a directory in the way. It might have + * contained references that have been deleted. If + * we don't require that the reference already + * exists, try to remove the directory so that it + * doesn't cause trouble when we want to rename the + * lockfile into place later. + */ + if (mustexist) { + /* Garden variety missing reference. */ + strbuf_addf(err, "unable to resolve reference '%s'", + refname); + goto error_return; + } else if (remove_dir_recursively(&ref_file, + REMOVE_DIR_EMPTY_ONLY)) { + if (refs_verify_refname_available( + &refs->base, refname, + extras, NULL, err)) { + /* + * The error message set by + * verify_refname_available() is OK. + */ + ret = TRANSACTION_NAME_CONFLICT; + goto error_return; + } else { + /* + * We can't delete the directory, + * but we also don't know of any + * references that it should + * contain. + */ + strbuf_addf(err, "there is a non-empty directory '%s' " + "blocking reference '%s'", + ref_file.buf, refname); + goto error_return; + } + } + } else if (failure_errno == EINVAL && (*type & REF_ISBROKEN)) { + strbuf_addf(err, "unable to resolve reference '%s': " + "reference broken", refname); + goto error_return; + } else { + strbuf_addf(err, "unable to resolve reference '%s': %s", + refname, strerror(failure_errno)); + goto error_return; + } + + /* + * If the ref did not exist and we are creating it, + * make sure there is no existing packed ref that + * conflicts with refname: + */ + if (refs_verify_refname_available( + refs->packed_ref_store, refname, + extras, NULL, err)) + goto error_return; + } + + ret = 0; + goto out; + +error_return: + unlock_ref(lock); + *lock_p = NULL; + +out: + strbuf_release(&ref_file); + return ret; +} + +struct files_ref_iterator { + struct ref_iterator base; + + struct ref_iterator *iter0; + struct repository *repo; + unsigned int flags; +}; + +static int files_ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + struct files_ref_iterator *iter = + (struct files_ref_iterator *)ref_iterator; + int ok; + + while ((ok = ref_iterator_advance(iter->iter0)) == ITER_OK) { + if (iter->flags & DO_FOR_EACH_PER_WORKTREE_ONLY && + parse_worktree_ref(iter->iter0->refname, NULL, NULL, + NULL) != REF_WORKTREE_CURRENT) + continue; + + if ((iter->flags & DO_FOR_EACH_OMIT_DANGLING_SYMREFS) && + (iter->iter0->flags & REF_ISSYMREF) && + (iter->iter0->flags & REF_ISBROKEN)) + continue; + + if (!(iter->flags & DO_FOR_EACH_INCLUDE_BROKEN) && + !ref_resolves_to_object(iter->iter0->refname, + iter->repo, + iter->iter0->oid, + iter->iter0->flags)) + continue; + + iter->base.refname = iter->iter0->refname; + iter->base.oid = iter->iter0->oid; + iter->base.flags = iter->iter0->flags; + return ITER_OK; + } + + iter->iter0 = NULL; + if (ref_iterator_abort(ref_iterator) != ITER_DONE) + ok = ITER_ERROR; + + return ok; +} + +static int files_ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) +{ + struct files_ref_iterator *iter = + (struct files_ref_iterator *)ref_iterator; + + return ref_iterator_peel(iter->iter0, peeled); +} + +static int files_ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + struct files_ref_iterator *iter = + (struct files_ref_iterator *)ref_iterator; + int ok = ITER_DONE; + + if (iter->iter0) + ok = ref_iterator_abort(iter->iter0); + + base_ref_iterator_free(ref_iterator); + return ok; +} + +static struct ref_iterator_vtable files_ref_iterator_vtable = { + .advance = files_ref_iterator_advance, + .peel = files_ref_iterator_peel, + .abort = files_ref_iterator_abort, +}; + +static struct ref_iterator *files_ref_iterator_begin( + struct ref_store *ref_store, + const char *prefix, unsigned int flags) +{ + struct files_ref_store *refs; + struct ref_iterator *loose_iter, *packed_iter, *overlay_iter; + struct files_ref_iterator *iter; + struct ref_iterator *ref_iterator; + unsigned int required_flags = REF_STORE_READ; + + if (!(flags & DO_FOR_EACH_INCLUDE_BROKEN)) + required_flags |= REF_STORE_ODB; + + refs = files_downcast(ref_store, required_flags, "ref_iterator_begin"); + + /* + * We must make sure that all loose refs are read before + * accessing the packed-refs file; this avoids a race + * condition if loose refs are migrated to the packed-refs + * file by a simultaneous process, but our in-memory view is + * from before the migration. We ensure this as follows: + * First, we call start the loose refs iteration with its + * `prime_ref` argument set to true. This causes the loose + * references in the subtree to be pre-read into the cache. + * (If they've already been read, that's OK; we only need to + * guarantee that they're read before the packed refs, not + * *how much* before.) After that, we call + * packed_ref_iterator_begin(), which internally checks + * whether the packed-ref cache is up to date with what is on + * disk, and re-reads it if not. + */ + + loose_iter = cache_ref_iterator_begin(get_loose_ref_cache(refs), + prefix, ref_store->repo, 1); + + /* + * The packed-refs file might contain broken references, for + * example an old version of a reference that points at an + * object that has since been garbage-collected. This is OK as + * long as there is a corresponding loose reference that + * overrides it, and we don't want to emit an error message in + * this case. So ask the packed_ref_store for all of its + * references, and (if needed) do our own check for broken + * ones in files_ref_iterator_advance(), after we have merged + * the packed and loose references. + */ + packed_iter = refs_ref_iterator_begin( + refs->packed_ref_store, prefix, 0, + DO_FOR_EACH_INCLUDE_BROKEN); + + overlay_iter = overlay_ref_iterator_begin(loose_iter, packed_iter); + + CALLOC_ARRAY(iter, 1); + ref_iterator = &iter->base; + base_ref_iterator_init(ref_iterator, &files_ref_iterator_vtable, + overlay_iter->ordered); + iter->iter0 = overlay_iter; + iter->repo = ref_store->repo; + iter->flags = flags; + + return ref_iterator; +} + +/* + * Callback function for raceproof_create_file(). This function is + * expected to do something that makes dirname(path) permanent despite + * the fact that other processes might be cleaning up empty + * directories at the same time. Usually it will create a file named + * path, but alternatively it could create another file in that + * directory, or even chdir() into that directory. The function should + * return 0 if the action was completed successfully. On error, it + * should return a nonzero result and set errno. + * raceproof_create_file() treats two errno values specially: + * + * - ENOENT -- dirname(path) does not exist. In this case, + * raceproof_create_file() tries creating dirname(path) + * (and any parent directories, if necessary) and calls + * the function again. + * + * - EISDIR -- the file already exists and is a directory. In this + * case, raceproof_create_file() removes the directory if + * it is empty (and recursively any empty directories that + * it contains) and calls the function again. + * + * Any other errno causes raceproof_create_file() to fail with the + * callback's return value and errno. + * + * Obviously, this function should be OK with being called again if it + * fails with ENOENT or EISDIR. In other scenarios it will not be + * called again. + */ +typedef int create_file_fn(const char *path, void *cb); + +/* + * Create a file in dirname(path) by calling fn, creating leading + * directories if necessary. Retry a few times in case we are racing + * with another process that is trying to clean up the directory that + * contains path. See the documentation for create_file_fn for more + * details. + * + * Return the value and set the errno that resulted from the most + * recent call of fn. fn is always called at least once, and will be + * called more than once if it returns ENOENT or EISDIR. + */ +static int raceproof_create_file(const char *path, create_file_fn fn, void *cb) +{ + /* + * The number of times we will try to remove empty directories + * in the way of path. This is only 1 because if another + * process is racily creating directories that conflict with + * us, we don't want to fight against them. + */ + int remove_directories_remaining = 1; + + /* + * The number of times that we will try to create the + * directories containing path. We are willing to attempt this + * more than once, because another process could be trying to + * clean up empty directories at the same time as we are + * trying to create them. + */ + int create_directories_remaining = 3; + + /* A scratch copy of path, filled lazily if we need it: */ + struct strbuf path_copy = STRBUF_INIT; + + int ret, save_errno; + + /* Sanity check: */ + assert(*path); + +retry_fn: + ret = fn(path, cb); + save_errno = errno; + if (!ret) + goto out; + + if (errno == EISDIR && remove_directories_remaining-- > 0) { + /* + * A directory is in the way. Maybe it is empty; try + * to remove it: + */ + if (!path_copy.len) + strbuf_addstr(&path_copy, path); + + if (!remove_dir_recursively(&path_copy, REMOVE_DIR_EMPTY_ONLY)) + goto retry_fn; + } else if (errno == ENOENT && create_directories_remaining-- > 0) { + /* + * Maybe the containing directory didn't exist, or + * maybe it was just deleted by a process that is + * racing with us to clean up empty directories. Try + * to create it: + */ + enum scld_error scld_result; + + if (!path_copy.len) + strbuf_addstr(&path_copy, path); + + do { + scld_result = safe_create_leading_directories(path_copy.buf); + if (scld_result == SCLD_OK) + goto retry_fn; + } while (scld_result == SCLD_VANISHED && create_directories_remaining-- > 0); + } + +out: + strbuf_release(&path_copy); + errno = save_errno; + return ret; +} + +static int remove_empty_directories(struct strbuf *path) +{ + /* + * we want to create a file but there is a directory there; + * if that is an empty directory (or a directory that contains + * only empty directories), remove them. + */ + return remove_dir_recursively(path, REMOVE_DIR_EMPTY_ONLY); +} + +static int create_reflock(const char *path, void *cb) +{ + struct lock_file *lk = cb; + + return hold_lock_file_for_update_timeout( + lk, path, LOCK_NO_DEREF, + get_files_ref_lock_timeout_ms()) < 0 ? -1 : 0; +} + +/* + * Locks a ref returning the lock on success and NULL on failure. + */ +static struct ref_lock *lock_ref_oid_basic(struct files_ref_store *refs, + const char *refname, + struct strbuf *err) +{ + struct strbuf ref_file = STRBUF_INIT; + struct ref_lock *lock; + + files_assert_main_repository(refs, "lock_ref_oid_basic"); + assert(err); + + CALLOC_ARRAY(lock, 1); + + files_ref_path(refs, &ref_file, refname); + + /* + * If the ref did not exist and we are creating it, make sure + * there is no existing packed ref whose name begins with our + * refname, nor a packed ref whose name is a proper prefix of + * our refname. + */ + if (is_null_oid(&lock->old_oid) && + refs_verify_refname_available(refs->packed_ref_store, refname, + NULL, NULL, err)) + goto error_return; + + lock->ref_name = xstrdup(refname); + + if (raceproof_create_file(ref_file.buf, create_reflock, &lock->lk)) { + unable_to_lock_message(ref_file.buf, errno, err); + goto error_return; + } + + if (!refs_resolve_ref_unsafe(&refs->base, lock->ref_name, 0, + &lock->old_oid, NULL)) + oidclr(&lock->old_oid); + goto out; + + error_return: + unlock_ref(lock); + lock = NULL; + + out: + strbuf_release(&ref_file); + return lock; +} + +struct ref_to_prune { + struct ref_to_prune *next; + struct object_id oid; + char name[FLEX_ARRAY]; +}; + +enum { + REMOVE_EMPTY_PARENTS_REF = 0x01, + REMOVE_EMPTY_PARENTS_REFLOG = 0x02 +}; + +/* + * Remove empty parent directories associated with the specified + * reference and/or its reflog, but spare [logs/]refs/ and immediate + * subdirs. flags is a combination of REMOVE_EMPTY_PARENTS_REF and/or + * REMOVE_EMPTY_PARENTS_REFLOG. + */ +static void try_remove_empty_parents(struct files_ref_store *refs, + const char *refname, + unsigned int flags) +{ + struct strbuf buf = STRBUF_INIT; + struct strbuf sb = STRBUF_INIT; + char *p, *q; + int i; + + strbuf_addstr(&buf, refname); + p = buf.buf; + for (i = 0; i < 2; i++) { /* refs/{heads,tags,...}/ */ + while (*p && *p != '/') + p++; + /* tolerate duplicate slashes; see check_refname_format() */ + while (*p == '/') + p++; + } + q = buf.buf + buf.len; + while (flags & (REMOVE_EMPTY_PARENTS_REF | REMOVE_EMPTY_PARENTS_REFLOG)) { + while (q > p && *q != '/') + q--; + while (q > p && *(q-1) == '/') + q--; + if (q == p) + break; + strbuf_setlen(&buf, q - buf.buf); + + strbuf_reset(&sb); + files_ref_path(refs, &sb, buf.buf); + if ((flags & REMOVE_EMPTY_PARENTS_REF) && rmdir(sb.buf)) + flags &= ~REMOVE_EMPTY_PARENTS_REF; + + strbuf_reset(&sb); + files_reflog_path(refs, &sb, buf.buf); + if ((flags & REMOVE_EMPTY_PARENTS_REFLOG) && rmdir(sb.buf)) + flags &= ~REMOVE_EMPTY_PARENTS_REFLOG; + } + strbuf_release(&buf); + strbuf_release(&sb); +} + +/* make sure nobody touched the ref, and unlink */ +static void prune_ref(struct files_ref_store *refs, struct ref_to_prune *r) +{ + struct ref_transaction *transaction; + struct strbuf err = STRBUF_INIT; + int ret = -1; + + if (check_refname_format(r->name, 0)) + return; + + transaction = ref_store_transaction_begin(&refs->base, &err); + if (!transaction) + goto cleanup; + ref_transaction_add_update( + transaction, r->name, + REF_NO_DEREF | REF_HAVE_NEW | REF_HAVE_OLD | REF_IS_PRUNING, + null_oid(), &r->oid, NULL); + if (ref_transaction_commit(transaction, &err)) + goto cleanup; + + ret = 0; + +cleanup: + if (ret) + error("%s", err.buf); + strbuf_release(&err); + ref_transaction_free(transaction); + return; +} + +/* + * Prune the loose versions of the references in the linked list + * `*refs_to_prune`, freeing the entries in the list as we go. + */ +static void prune_refs(struct files_ref_store *refs, struct ref_to_prune **refs_to_prune) +{ + while (*refs_to_prune) { + struct ref_to_prune *r = *refs_to_prune; + *refs_to_prune = r->next; + prune_ref(refs, r); + free(r); + } +} + +/* + * Return true if the specified reference should be packed. + */ +static int should_pack_ref(const char *refname, + const struct object_id *oid, unsigned int ref_flags, + unsigned int pack_flags) +{ + /* Do not pack per-worktree refs: */ + if (parse_worktree_ref(refname, NULL, NULL, NULL) != + REF_WORKTREE_SHARED) + return 0; + + /* Do not pack non-tags unless PACK_REFS_ALL is set: */ + if (!(pack_flags & PACK_REFS_ALL) && !starts_with(refname, "refs/tags/")) + return 0; + + /* Do not pack symbolic refs: */ + if (ref_flags & REF_ISSYMREF) + return 0; + + /* Do not pack broken refs: */ + if (!ref_resolves_to_object(refname, the_repository, oid, ref_flags)) + return 0; + + return 1; +} + +static int files_pack_refs(struct ref_store *ref_store, unsigned int flags) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_WRITE | REF_STORE_ODB, + "pack_refs"); + struct ref_iterator *iter; + int ok; + struct ref_to_prune *refs_to_prune = NULL; + struct strbuf err = STRBUF_INIT; + struct ref_transaction *transaction; + + transaction = ref_store_transaction_begin(refs->packed_ref_store, &err); + if (!transaction) + return -1; + + packed_refs_lock(refs->packed_ref_store, LOCK_DIE_ON_ERROR, &err); + + iter = cache_ref_iterator_begin(get_loose_ref_cache(refs), NULL, + the_repository, 0); + while ((ok = ref_iterator_advance(iter)) == ITER_OK) { + /* + * If the loose reference can be packed, add an entry + * in the packed ref cache. If the reference should be + * pruned, also add it to refs_to_prune. + */ + if (!should_pack_ref(iter->refname, iter->oid, iter->flags, + flags)) + continue; + + /* + * Add a reference creation for this reference to the + * packed-refs transaction: + */ + if (ref_transaction_update(transaction, iter->refname, + iter->oid, NULL, + REF_NO_DEREF, NULL, &err)) + die("failure preparing to create packed reference %s: %s", + iter->refname, err.buf); + + /* Schedule the loose reference for pruning if requested. */ + if ((flags & PACK_REFS_PRUNE)) { + struct ref_to_prune *n; + FLEX_ALLOC_STR(n, name, iter->refname); + oidcpy(&n->oid, iter->oid); + n->next = refs_to_prune; + refs_to_prune = n; + } + } + if (ok != ITER_DONE) + die("error while iterating over references"); + + if (ref_transaction_commit(transaction, &err)) + die("unable to write new packed-refs: %s", err.buf); + + ref_transaction_free(transaction); + + packed_refs_unlock(refs->packed_ref_store); + + prune_refs(refs, &refs_to_prune); + strbuf_release(&err); + return 0; +} + +static int files_delete_refs(struct ref_store *ref_store, const char *msg, + struct string_list *refnames, unsigned int flags) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_WRITE, "delete_refs"); + struct strbuf err = STRBUF_INIT; + int i, result = 0; + + if (!refnames->nr) + return 0; + + if (packed_refs_lock(refs->packed_ref_store, 0, &err)) + goto error; + + if (refs_delete_refs(refs->packed_ref_store, msg, refnames, flags)) { + packed_refs_unlock(refs->packed_ref_store); + goto error; + } + + packed_refs_unlock(refs->packed_ref_store); + + for (i = 0; i < refnames->nr; i++) { + const char *refname = refnames->items[i].string; + + if (refs_delete_ref(&refs->base, msg, refname, NULL, flags)) + result |= error(_("could not remove reference %s"), refname); + } + + strbuf_release(&err); + return result; + +error: + /* + * If we failed to rewrite the packed-refs file, then it is + * unsafe to try to remove loose refs, because doing so might + * expose an obsolete packed value for a reference that might + * even point at an object that has been garbage collected. + */ + if (refnames->nr == 1) + error(_("could not delete reference %s: %s"), + refnames->items[0].string, err.buf); + else + error(_("could not delete references: %s"), err.buf); + + strbuf_release(&err); + return -1; +} + +/* + * People using contrib's git-new-workdir have .git/logs/refs -> + * /some/other/path/.git/logs/refs, and that may live on another device. + * + * IOW, to avoid cross device rename errors, the temporary renamed log must + * live into logs/refs. + */ +#define TMP_RENAMED_LOG "refs/.tmp-renamed-log" + +struct rename_cb { + const char *tmp_renamed_log; + int true_errno; +}; + +static int rename_tmp_log_callback(const char *path, void *cb_data) +{ + struct rename_cb *cb = cb_data; + + if (rename(cb->tmp_renamed_log, path)) { + /* + * rename(a, b) when b is an existing directory ought + * to result in ISDIR, but Solaris 5.8 gives ENOTDIR. + * Sheesh. Record the true errno for error reporting, + * but report EISDIR to raceproof_create_file() so + * that it knows to retry. + */ + cb->true_errno = errno; + if (errno == ENOTDIR) + errno = EISDIR; + return -1; + } else { + return 0; + } +} + +static int rename_tmp_log(struct files_ref_store *refs, const char *newrefname) +{ + struct strbuf path = STRBUF_INIT; + struct strbuf tmp = STRBUF_INIT; + struct rename_cb cb; + int ret; + + files_reflog_path(refs, &path, newrefname); + files_reflog_path(refs, &tmp, TMP_RENAMED_LOG); + cb.tmp_renamed_log = tmp.buf; + ret = raceproof_create_file(path.buf, rename_tmp_log_callback, &cb); + if (ret) { + if (errno == EISDIR) + error("directory not empty: %s", path.buf); + else + error("unable to move logfile %s to %s: %s", + tmp.buf, path.buf, + strerror(cb.true_errno)); + } + + strbuf_release(&path); + strbuf_release(&tmp); + return ret; +} + +static int write_ref_to_lockfile(struct ref_lock *lock, + const struct object_id *oid, + int skip_oid_verification, struct strbuf *err); +static int commit_ref_update(struct files_ref_store *refs, + struct ref_lock *lock, + const struct object_id *oid, const char *logmsg, + struct strbuf *err); + +/* + * Emit a better error message than lockfile.c's + * unable_to_lock_message() would in case there is a D/F conflict with + * another existing reference. If there would be a conflict, emit an error + * message and return false; otherwise, return true. + * + * Note that this function is not safe against all races with other + * processes, and that's not its job. We'll emit a more verbose error on D/f + * conflicts if we get past it into lock_ref_oid_basic(). + */ +static int refs_rename_ref_available(struct ref_store *refs, + const char *old_refname, + const char *new_refname) +{ + struct string_list skip = STRING_LIST_INIT_NODUP; + struct strbuf err = STRBUF_INIT; + int ok; + + string_list_insert(&skip, old_refname); + ok = !refs_verify_refname_available(refs, new_refname, + NULL, &skip, &err); + if (!ok) + error("%s", err.buf); + + string_list_clear(&skip, 0); + strbuf_release(&err); + return ok; +} + +static int files_copy_or_rename_ref(struct ref_store *ref_store, + const char *oldrefname, const char *newrefname, + const char *logmsg, int copy) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_WRITE, "rename_ref"); + struct object_id orig_oid; + int flag = 0, logmoved = 0; + struct ref_lock *lock; + struct stat loginfo; + struct strbuf sb_oldref = STRBUF_INIT; + struct strbuf sb_newref = STRBUF_INIT; + struct strbuf tmp_renamed_log = STRBUF_INIT; + int log, ret; + struct strbuf err = STRBUF_INIT; + + files_reflog_path(refs, &sb_oldref, oldrefname); + files_reflog_path(refs, &sb_newref, newrefname); + files_reflog_path(refs, &tmp_renamed_log, TMP_RENAMED_LOG); + + log = !lstat(sb_oldref.buf, &loginfo); + if (log && S_ISLNK(loginfo.st_mode)) { + ret = error("reflog for %s is a symlink", oldrefname); + goto out; + } + + if (!refs_resolve_ref_unsafe(&refs->base, oldrefname, + RESOLVE_REF_READING | RESOLVE_REF_NO_RECURSE, + &orig_oid, &flag)) { + ret = error("refname %s not found", oldrefname); + goto out; + } + + if (flag & REF_ISSYMREF) { + if (copy) + ret = error("refname %s is a symbolic ref, copying it is not supported", + oldrefname); + else + ret = error("refname %s is a symbolic ref, renaming it is not supported", + oldrefname); + goto out; + } + if (!refs_rename_ref_available(&refs->base, oldrefname, newrefname)) { + ret = 1; + goto out; + } + + if (!copy && log && rename(sb_oldref.buf, tmp_renamed_log.buf)) { + ret = error("unable to move logfile logs/%s to logs/"TMP_RENAMED_LOG": %s", + oldrefname, strerror(errno)); + goto out; + } + + if (copy && log && copy_file(tmp_renamed_log.buf, sb_oldref.buf, 0644)) { + ret = error("unable to copy logfile logs/%s to logs/"TMP_RENAMED_LOG": %s", + oldrefname, strerror(errno)); + goto out; + } + + if (!copy && refs_delete_ref(&refs->base, logmsg, oldrefname, + &orig_oid, REF_NO_DEREF)) { + error("unable to delete old %s", oldrefname); + goto rollback; + } + + /* + * Since we are doing a shallow lookup, oid is not the + * correct value to pass to delete_ref as old_oid. But that + * doesn't matter, because an old_oid check wouldn't add to + * the safety anyway; we want to delete the reference whatever + * its current value. + */ + if (!copy && refs_resolve_ref_unsafe(&refs->base, newrefname, + RESOLVE_REF_READING | RESOLVE_REF_NO_RECURSE, + NULL, NULL) && + refs_delete_ref(&refs->base, NULL, newrefname, + NULL, REF_NO_DEREF)) { + if (errno == EISDIR) { + struct strbuf path = STRBUF_INIT; + int result; + + files_ref_path(refs, &path, newrefname); + result = remove_empty_directories(&path); + strbuf_release(&path); + + if (result) { + error("Directory not empty: %s", newrefname); + goto rollback; + } + } else { + error("unable to delete existing %s", newrefname); + goto rollback; + } + } + + if (log && rename_tmp_log(refs, newrefname)) + goto rollback; + + logmoved = log; + + lock = lock_ref_oid_basic(refs, newrefname, &err); + if (!lock) { + if (copy) + error("unable to copy '%s' to '%s': %s", oldrefname, newrefname, err.buf); + else + error("unable to rename '%s' to '%s': %s", oldrefname, newrefname, err.buf); + strbuf_release(&err); + goto rollback; + } + oidcpy(&lock->old_oid, &orig_oid); + + if (write_ref_to_lockfile(lock, &orig_oid, 0, &err) || + commit_ref_update(refs, lock, &orig_oid, logmsg, &err)) { + error("unable to write current sha1 into %s: %s", newrefname, err.buf); + strbuf_release(&err); + goto rollback; + } + + ret = 0; + goto out; + + rollback: + lock = lock_ref_oid_basic(refs, oldrefname, &err); + if (!lock) { + error("unable to lock %s for rollback: %s", oldrefname, err.buf); + strbuf_release(&err); + goto rollbacklog; + } + + flag = log_all_ref_updates; + log_all_ref_updates = LOG_REFS_NONE; + if (write_ref_to_lockfile(lock, &orig_oid, 0, &err) || + commit_ref_update(refs, lock, &orig_oid, NULL, &err)) { + error("unable to write current sha1 into %s: %s", oldrefname, err.buf); + strbuf_release(&err); + } + log_all_ref_updates = flag; + + rollbacklog: + if (logmoved && rename(sb_newref.buf, sb_oldref.buf)) + error("unable to restore logfile %s from %s: %s", + oldrefname, newrefname, strerror(errno)); + if (!logmoved && log && + rename(tmp_renamed_log.buf, sb_oldref.buf)) + error("unable to restore logfile %s from logs/"TMP_RENAMED_LOG": %s", + oldrefname, strerror(errno)); + ret = 1; + out: + strbuf_release(&sb_newref); + strbuf_release(&sb_oldref); + strbuf_release(&tmp_renamed_log); + + return ret; +} + +static int files_rename_ref(struct ref_store *ref_store, + const char *oldrefname, const char *newrefname, + const char *logmsg) +{ + return files_copy_or_rename_ref(ref_store, oldrefname, + newrefname, logmsg, 0); +} + +static int files_copy_ref(struct ref_store *ref_store, + const char *oldrefname, const char *newrefname, + const char *logmsg) +{ + return files_copy_or_rename_ref(ref_store, oldrefname, + newrefname, logmsg, 1); +} + +static int close_ref_gently(struct ref_lock *lock) +{ + if (close_lock_file_gently(&lock->lk)) + return -1; + return 0; +} + +static int commit_ref(struct ref_lock *lock) +{ + char *path = get_locked_file_path(&lock->lk); + struct stat st; + + if (!lstat(path, &st) && S_ISDIR(st.st_mode)) { + /* + * There is a directory at the path we want to rename + * the lockfile to. Hopefully it is empty; try to + * delete it. + */ + size_t len = strlen(path); + struct strbuf sb_path = STRBUF_INIT; + + strbuf_attach(&sb_path, path, len, len); + + /* + * If this fails, commit_lock_file() will also fail + * and will report the problem. + */ + remove_empty_directories(&sb_path); + strbuf_release(&sb_path); + } else { + free(path); + } + + if (commit_lock_file(&lock->lk)) + return -1; + return 0; +} + +static int open_or_create_logfile(const char *path, void *cb) +{ + int *fd = cb; + + *fd = open(path, O_APPEND | O_WRONLY | O_CREAT, 0666); + return (*fd < 0) ? -1 : 0; +} + +/* + * Create a reflog for a ref. If force_create = 0, only create the + * reflog for certain refs (those for which should_autocreate_reflog + * returns non-zero). Otherwise, create it regardless of the reference + * name. If the logfile already existed or was created, return 0 and + * set *logfd to the file descriptor opened for appending to the file. + * If no logfile exists and we decided not to create one, return 0 and + * set *logfd to -1. On failure, fill in *err, set *logfd to -1, and + * return -1. + */ +static int log_ref_setup(struct files_ref_store *refs, + const char *refname, int force_create, + int *logfd, struct strbuf *err) +{ + struct strbuf logfile_sb = STRBUF_INIT; + char *logfile; + + files_reflog_path(refs, &logfile_sb, refname); + logfile = strbuf_detach(&logfile_sb, NULL); + + if (force_create || should_autocreate_reflog(refname)) { + if (raceproof_create_file(logfile, open_or_create_logfile, logfd)) { + if (errno == ENOENT) + strbuf_addf(err, "unable to create directory for '%s': " + "%s", logfile, strerror(errno)); + else if (errno == EISDIR) + strbuf_addf(err, "there are still logs under '%s'", + logfile); + else + strbuf_addf(err, "unable to append to '%s': %s", + logfile, strerror(errno)); + + goto error; + } + } else { + *logfd = open(logfile, O_APPEND | O_WRONLY); + if (*logfd < 0) { + if (errno == ENOENT || errno == EISDIR) { + /* + * The logfile doesn't already exist, + * but that is not an error; it only + * means that we won't write log + * entries to it. + */ + ; + } else { + strbuf_addf(err, "unable to append to '%s': %s", + logfile, strerror(errno)); + goto error; + } + } + } + + if (*logfd >= 0) + adjust_shared_perm(logfile); + + free(logfile); + return 0; + +error: + free(logfile); + return -1; +} + +static int files_create_reflog(struct ref_store *ref_store, const char *refname, + struct strbuf *err) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_WRITE, "create_reflog"); + int fd; + + if (log_ref_setup(refs, refname, 1, &fd, err)) + return -1; + + if (fd >= 0) + close(fd); + + return 0; +} + +static int log_ref_write_fd(int fd, const struct object_id *old_oid, + const struct object_id *new_oid, + const char *committer, const char *msg) +{ + struct strbuf sb = STRBUF_INIT; + int ret = 0; + + strbuf_addf(&sb, "%s %s %s", oid_to_hex(old_oid), oid_to_hex(new_oid), committer); + if (msg && *msg) { + strbuf_addch(&sb, '\t'); + strbuf_addstr(&sb, msg); + } + strbuf_addch(&sb, '\n'); + if (write_in_full(fd, sb.buf, sb.len) < 0) + ret = -1; + strbuf_release(&sb); + return ret; +} + +static int files_log_ref_write(struct files_ref_store *refs, + const char *refname, const struct object_id *old_oid, + const struct object_id *new_oid, const char *msg, + int flags, struct strbuf *err) +{ + int logfd, result; + + if (log_all_ref_updates == LOG_REFS_UNSET) + log_all_ref_updates = is_bare_repository() ? LOG_REFS_NONE : LOG_REFS_NORMAL; + + result = log_ref_setup(refs, refname, + flags & REF_FORCE_CREATE_REFLOG, + &logfd, err); + + if (result) + return result; + + if (logfd < 0) + return 0; + result = log_ref_write_fd(logfd, old_oid, new_oid, + git_committer_info(0), msg); + if (result) { + struct strbuf sb = STRBUF_INIT; + int save_errno = errno; + + files_reflog_path(refs, &sb, refname); + strbuf_addf(err, "unable to append to '%s': %s", + sb.buf, strerror(save_errno)); + strbuf_release(&sb); + close(logfd); + return -1; + } + if (close(logfd)) { + struct strbuf sb = STRBUF_INIT; + int save_errno = errno; + + files_reflog_path(refs, &sb, refname); + strbuf_addf(err, "unable to append to '%s': %s", + sb.buf, strerror(save_errno)); + strbuf_release(&sb); + return -1; + } + return 0; +} + +/* + * Write oid into the open lockfile, then close the lockfile. On + * errors, rollback the lockfile, fill in *err and return -1. + */ +static int write_ref_to_lockfile(struct ref_lock *lock, + const struct object_id *oid, + int skip_oid_verification, struct strbuf *err) +{ + static char term = '\n'; + struct object *o; + int fd; + + if (!skip_oid_verification) { + o = parse_object(the_repository, oid); + if (!o) { + strbuf_addf( + err, + "trying to write ref '%s' with nonexistent object %s", + lock->ref_name, oid_to_hex(oid)); + unlock_ref(lock); + return -1; + } + if (o->type != OBJ_COMMIT && is_branch(lock->ref_name)) { + strbuf_addf( + err, + "trying to write non-commit object %s to branch '%s'", + oid_to_hex(oid), lock->ref_name); + unlock_ref(lock); + return -1; + } + } + fd = get_lock_file_fd(&lock->lk); + if (write_in_full(fd, oid_to_hex(oid), the_hash_algo->hexsz) < 0 || + write_in_full(fd, &term, 1) < 0 || + fsync_component(FSYNC_COMPONENT_REFERENCE, get_lock_file_fd(&lock->lk)) < 0 || + close_ref_gently(lock) < 0) { + strbuf_addf(err, + "couldn't write '%s'", get_lock_file_path(&lock->lk)); + unlock_ref(lock); + return -1; + } + return 0; +} + +/* + * Commit a change to a loose reference that has already been written + * to the loose reference lockfile. Also update the reflogs if + * necessary, using the specified lockmsg (which can be NULL). + */ +static int commit_ref_update(struct files_ref_store *refs, + struct ref_lock *lock, + const struct object_id *oid, const char *logmsg, + struct strbuf *err) +{ + files_assert_main_repository(refs, "commit_ref_update"); + + clear_loose_ref_cache(refs); + if (files_log_ref_write(refs, lock->ref_name, + &lock->old_oid, oid, + logmsg, 0, err)) { + char *old_msg = strbuf_detach(err, NULL); + strbuf_addf(err, "cannot update the ref '%s': %s", + lock->ref_name, old_msg); + free(old_msg); + unlock_ref(lock); + return -1; + } + + if (strcmp(lock->ref_name, "HEAD") != 0) { + /* + * Special hack: If a branch is updated directly and HEAD + * points to it (may happen on the remote side of a push + * for example) then logically the HEAD reflog should be + * updated too. + * A generic solution implies reverse symref information, + * but finding all symrefs pointing to the given branch + * would be rather costly for this rare event (the direct + * update of a branch) to be worth it. So let's cheat and + * check with HEAD only which should cover 99% of all usage + * scenarios (even 100% of the default ones). + */ + int head_flag; + const char *head_ref; + + head_ref = refs_resolve_ref_unsafe(&refs->base, "HEAD", + RESOLVE_REF_READING, + NULL, &head_flag); + if (head_ref && (head_flag & REF_ISSYMREF) && + !strcmp(head_ref, lock->ref_name)) { + struct strbuf log_err = STRBUF_INIT; + if (files_log_ref_write(refs, "HEAD", + &lock->old_oid, oid, + logmsg, 0, &log_err)) { + error("%s", log_err.buf); + strbuf_release(&log_err); + } + } + } + + if (commit_ref(lock)) { + strbuf_addf(err, "couldn't set '%s'", lock->ref_name); + unlock_ref(lock); + return -1; + } + + unlock_ref(lock); + return 0; +} + +static int create_ref_symlink(struct ref_lock *lock, const char *target) +{ + int ret = -1; +#ifndef NO_SYMLINK_HEAD + char *ref_path = get_locked_file_path(&lock->lk); + unlink(ref_path); + ret = symlink(target, ref_path); + free(ref_path); + + if (ret) + fprintf(stderr, "no symlink - falling back to symbolic ref\n"); +#endif + return ret; +} + +static void update_symref_reflog(struct files_ref_store *refs, + struct ref_lock *lock, const char *refname, + const char *target, const char *logmsg) +{ + struct strbuf err = STRBUF_INIT; + struct object_id new_oid; + + if (logmsg && + refs_resolve_ref_unsafe(&refs->base, target, + RESOLVE_REF_READING, &new_oid, NULL) && + files_log_ref_write(refs, refname, &lock->old_oid, + &new_oid, logmsg, 0, &err)) { + error("%s", err.buf); + strbuf_release(&err); + } +} + +static int create_symref_locked(struct files_ref_store *refs, + struct ref_lock *lock, const char *refname, + const char *target, const char *logmsg) +{ + if (prefer_symlink_refs && !create_ref_symlink(lock, target)) { + update_symref_reflog(refs, lock, refname, target, logmsg); + return 0; + } + + if (!fdopen_lock_file(&lock->lk, "w")) + return error("unable to fdopen %s: %s", + get_lock_file_path(&lock->lk), strerror(errno)); + + update_symref_reflog(refs, lock, refname, target, logmsg); + + /* no error check; commit_ref will check ferror */ + fprintf(get_lock_file_fp(&lock->lk), "ref: %s\n", target); + if (commit_ref(lock) < 0) + return error("unable to write symref for %s: %s", refname, + strerror(errno)); + return 0; +} + +static int files_create_symref(struct ref_store *ref_store, + const char *refname, const char *target, + const char *logmsg) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_WRITE, "create_symref"); + struct strbuf err = STRBUF_INIT; + struct ref_lock *lock; + int ret; + + lock = lock_ref_oid_basic(refs, refname, &err); + if (!lock) { + error("%s", err.buf); + strbuf_release(&err); + return -1; + } + + ret = create_symref_locked(refs, lock, refname, target, logmsg); + unlock_ref(lock); + return ret; +} + +static int files_reflog_exists(struct ref_store *ref_store, + const char *refname) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_READ, "reflog_exists"); + struct strbuf sb = STRBUF_INIT; + struct stat st; + int ret; + + files_reflog_path(refs, &sb, refname); + ret = !lstat(sb.buf, &st) && S_ISREG(st.st_mode); + strbuf_release(&sb); + return ret; +} + +static int files_delete_reflog(struct ref_store *ref_store, + const char *refname) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_WRITE, "delete_reflog"); + struct strbuf sb = STRBUF_INIT; + int ret; + + files_reflog_path(refs, &sb, refname); + ret = remove_path(sb.buf); + strbuf_release(&sb); + return ret; +} + +static int show_one_reflog_ent(struct strbuf *sb, each_reflog_ent_fn fn, void *cb_data) +{ + struct object_id ooid, noid; + char *email_end, *message; + timestamp_t timestamp; + int tz; + const char *p = sb->buf; + + /* old SP new SP name <email> SP time TAB msg LF */ + if (!sb->len || sb->buf[sb->len - 1] != '\n' || + parse_oid_hex(p, &ooid, &p) || *p++ != ' ' || + parse_oid_hex(p, &noid, &p) || *p++ != ' ' || + !(email_end = strchr(p, '>')) || + email_end[1] != ' ' || + !(timestamp = parse_timestamp(email_end + 2, &message, 10)) || + !message || message[0] != ' ' || + (message[1] != '+' && message[1] != '-') || + !isdigit(message[2]) || !isdigit(message[3]) || + !isdigit(message[4]) || !isdigit(message[5])) + return 0; /* corrupt? */ + email_end[1] = '\0'; + tz = strtol(message + 1, NULL, 10); + if (message[6] != '\t') + message += 6; + else + message += 7; + return fn(&ooid, &noid, p, timestamp, tz, message, cb_data); +} + +static char *find_beginning_of_line(char *bob, char *scan) +{ + while (bob < scan && *(--scan) != '\n') + ; /* keep scanning backwards */ + /* + * Return either beginning of the buffer, or LF at the end of + * the previous line. + */ + return scan; +} + +static int files_for_each_reflog_ent_reverse(struct ref_store *ref_store, + const char *refname, + each_reflog_ent_fn fn, + void *cb_data) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_READ, + "for_each_reflog_ent_reverse"); + struct strbuf sb = STRBUF_INIT; + FILE *logfp; + long pos; + int ret = 0, at_tail = 1; + + files_reflog_path(refs, &sb, refname); + logfp = fopen(sb.buf, "r"); + strbuf_release(&sb); + if (!logfp) + return -1; + + /* Jump to the end */ + if (fseek(logfp, 0, SEEK_END) < 0) + ret = error("cannot seek back reflog for %s: %s", + refname, strerror(errno)); + pos = ftell(logfp); + while (!ret && 0 < pos) { + int cnt; + size_t nread; + char buf[BUFSIZ]; + char *endp, *scanp; + + /* Fill next block from the end */ + cnt = (sizeof(buf) < pos) ? sizeof(buf) : pos; + if (fseek(logfp, pos - cnt, SEEK_SET)) { + ret = error("cannot seek back reflog for %s: %s", + refname, strerror(errno)); + break; + } + nread = fread(buf, cnt, 1, logfp); + if (nread != 1) { + ret = error("cannot read %d bytes from reflog for %s: %s", + cnt, refname, strerror(errno)); + break; + } + pos -= cnt; + + scanp = endp = buf + cnt; + if (at_tail && scanp[-1] == '\n') + /* Looking at the final LF at the end of the file */ + scanp--; + at_tail = 0; + + while (buf < scanp) { + /* + * terminating LF of the previous line, or the beginning + * of the buffer. + */ + char *bp; + + bp = find_beginning_of_line(buf, scanp); + + if (*bp == '\n') { + /* + * The newline is the end of the previous line, + * so we know we have complete line starting + * at (bp + 1). Prefix it onto any prior data + * we collected for the line and process it. + */ + strbuf_splice(&sb, 0, 0, bp + 1, endp - (bp + 1)); + scanp = bp; + endp = bp + 1; + ret = show_one_reflog_ent(&sb, fn, cb_data); + strbuf_reset(&sb); + if (ret) + break; + } else if (!pos) { + /* + * We are at the start of the buffer, and the + * start of the file; there is no previous + * line, and we have everything for this one. + * Process it, and we can end the loop. + */ + strbuf_splice(&sb, 0, 0, buf, endp - buf); + ret = show_one_reflog_ent(&sb, fn, cb_data); + strbuf_reset(&sb); + break; + } + + if (bp == buf) { + /* + * We are at the start of the buffer, and there + * is more file to read backwards. Which means + * we are in the middle of a line. Note that we + * may get here even if *bp was a newline; that + * just means we are at the exact end of the + * previous line, rather than some spot in the + * middle. + * + * Save away what we have to be combined with + * the data from the next read. + */ + strbuf_splice(&sb, 0, 0, buf, endp - buf); + break; + } + } + + } + if (!ret && sb.len) + BUG("reverse reflog parser had leftover data"); + + fclose(logfp); + strbuf_release(&sb); + return ret; +} + +static int files_for_each_reflog_ent(struct ref_store *ref_store, + const char *refname, + each_reflog_ent_fn fn, void *cb_data) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_READ, + "for_each_reflog_ent"); + FILE *logfp; + struct strbuf sb = STRBUF_INIT; + int ret = 0; + + files_reflog_path(refs, &sb, refname); + logfp = fopen(sb.buf, "r"); + strbuf_release(&sb); + if (!logfp) + return -1; + + while (!ret && !strbuf_getwholeline(&sb, logfp, '\n')) + ret = show_one_reflog_ent(&sb, fn, cb_data); + fclose(logfp); + strbuf_release(&sb); + return ret; +} + +struct files_reflog_iterator { + struct ref_iterator base; + + struct ref_store *ref_store; + struct dir_iterator *dir_iterator; + struct object_id oid; +}; + +static int files_reflog_iterator_advance(struct ref_iterator *ref_iterator) +{ + struct files_reflog_iterator *iter = + (struct files_reflog_iterator *)ref_iterator; + struct dir_iterator *diter = iter->dir_iterator; + int ok; + + while ((ok = dir_iterator_advance(diter)) == ITER_OK) { + int flags; + + if (!S_ISREG(diter->st.st_mode)) + continue; + if (diter->basename[0] == '.') + continue; + if (ends_with(diter->basename, ".lock")) + continue; + + if (!refs_resolve_ref_unsafe(iter->ref_store, + diter->relative_path, 0, + &iter->oid, &flags)) { + error("bad ref for %s", diter->path.buf); + continue; + } + + iter->base.refname = diter->relative_path; + iter->base.oid = &iter->oid; + iter->base.flags = flags; + return ITER_OK; + } + + iter->dir_iterator = NULL; + if (ref_iterator_abort(ref_iterator) == ITER_ERROR) + ok = ITER_ERROR; + return ok; +} + +static int files_reflog_iterator_peel(struct ref_iterator *ref_iterator UNUSED, + struct object_id *peeled UNUSED) +{ + BUG("ref_iterator_peel() called for reflog_iterator"); +} + +static int files_reflog_iterator_abort(struct ref_iterator *ref_iterator) +{ + struct files_reflog_iterator *iter = + (struct files_reflog_iterator *)ref_iterator; + int ok = ITER_DONE; + + if (iter->dir_iterator) + ok = dir_iterator_abort(iter->dir_iterator); + + base_ref_iterator_free(ref_iterator); + return ok; +} + +static struct ref_iterator_vtable files_reflog_iterator_vtable = { + .advance = files_reflog_iterator_advance, + .peel = files_reflog_iterator_peel, + .abort = files_reflog_iterator_abort, +}; + +static struct ref_iterator *reflog_iterator_begin(struct ref_store *ref_store, + const char *gitdir) +{ + struct dir_iterator *diter; + struct files_reflog_iterator *iter; + struct ref_iterator *ref_iterator; + struct strbuf sb = STRBUF_INIT; + + strbuf_addf(&sb, "%s/logs", gitdir); + + diter = dir_iterator_begin(sb.buf, 0); + if (!diter) { + strbuf_release(&sb); + return empty_ref_iterator_begin(); + } + + CALLOC_ARRAY(iter, 1); + ref_iterator = &iter->base; + + base_ref_iterator_init(ref_iterator, &files_reflog_iterator_vtable, 0); + iter->dir_iterator = diter; + iter->ref_store = ref_store; + strbuf_release(&sb); + + return ref_iterator; +} + +static enum iterator_selection reflog_iterator_select( + struct ref_iterator *iter_worktree, + struct ref_iterator *iter_common, + void *cb_data UNUSED) +{ + if (iter_worktree) { + /* + * We're a bit loose here. We probably should ignore + * common refs if they are accidentally added as + * per-worktree refs. + */ + return ITER_SELECT_0; + } else if (iter_common) { + if (parse_worktree_ref(iter_common->refname, NULL, NULL, + NULL) == REF_WORKTREE_SHARED) + return ITER_SELECT_1; + + /* + * The main ref store may contain main worktree's + * per-worktree refs, which should be ignored + */ + return ITER_SKIP_1; + } else + return ITER_DONE; +} + +static struct ref_iterator *files_reflog_iterator_begin(struct ref_store *ref_store) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_READ, + "reflog_iterator_begin"); + + if (!strcmp(refs->base.gitdir, refs->gitcommondir)) { + return reflog_iterator_begin(ref_store, refs->gitcommondir); + } else { + return merge_ref_iterator_begin( + 0, reflog_iterator_begin(ref_store, refs->base.gitdir), + reflog_iterator_begin(ref_store, refs->gitcommondir), + reflog_iterator_select, refs); + } +} + +/* + * If update is a direct update of head_ref (the reference pointed to + * by HEAD), then add an extra REF_LOG_ONLY update for HEAD. + */ +static int split_head_update(struct ref_update *update, + struct ref_transaction *transaction, + const char *head_ref, + struct string_list *affected_refnames, + struct strbuf *err) +{ + struct string_list_item *item; + struct ref_update *new_update; + + if ((update->flags & REF_LOG_ONLY) || + (update->flags & REF_IS_PRUNING) || + (update->flags & REF_UPDATE_VIA_HEAD)) + return 0; + + if (strcmp(update->refname, head_ref)) + return 0; + + /* + * First make sure that HEAD is not already in the + * transaction. This check is O(lg N) in the transaction + * size, but it happens at most once per transaction. + */ + if (string_list_has_string(affected_refnames, "HEAD")) { + /* An entry already existed */ + strbuf_addf(err, + "multiple updates for 'HEAD' (including one " + "via its referent '%s') are not allowed", + update->refname); + return TRANSACTION_NAME_CONFLICT; + } + + new_update = ref_transaction_add_update( + transaction, "HEAD", + update->flags | REF_LOG_ONLY | REF_NO_DEREF, + &update->new_oid, &update->old_oid, + update->msg); + + /* + * Add "HEAD". This insertion is O(N) in the transaction + * size, but it happens at most once per transaction. + * Add new_update->refname instead of a literal "HEAD". + */ + if (strcmp(new_update->refname, "HEAD")) + BUG("%s unexpectedly not 'HEAD'", new_update->refname); + item = string_list_insert(affected_refnames, new_update->refname); + item->util = new_update; + + return 0; +} + +/* + * update is for a symref that points at referent and doesn't have + * REF_NO_DEREF set. Split it into two updates: + * - The original update, but with REF_LOG_ONLY and REF_NO_DEREF set + * - A new, separate update for the referent reference + * Note that the new update will itself be subject to splitting when + * the iteration gets to it. + */ +static int split_symref_update(struct ref_update *update, + const char *referent, + struct ref_transaction *transaction, + struct string_list *affected_refnames, + struct strbuf *err) +{ + struct string_list_item *item; + struct ref_update *new_update; + unsigned int new_flags; + + /* + * First make sure that referent is not already in the + * transaction. This check is O(lg N) in the transaction + * size, but it happens at most once per symref in a + * transaction. + */ + if (string_list_has_string(affected_refnames, referent)) { + /* An entry already exists */ + strbuf_addf(err, + "multiple updates for '%s' (including one " + "via symref '%s') are not allowed", + referent, update->refname); + return TRANSACTION_NAME_CONFLICT; + } + + new_flags = update->flags; + if (!strcmp(update->refname, "HEAD")) { + /* + * Record that the new update came via HEAD, so that + * when we process it, split_head_update() doesn't try + * to add another reflog update for HEAD. Note that + * this bit will be propagated if the new_update + * itself needs to be split. + */ + new_flags |= REF_UPDATE_VIA_HEAD; + } + + new_update = ref_transaction_add_update( + transaction, referent, new_flags, + &update->new_oid, &update->old_oid, + update->msg); + + new_update->parent_update = update; + + /* + * Change the symbolic ref update to log only. Also, it + * doesn't need to check its old OID value, as that will be + * done when new_update is processed. + */ + update->flags |= REF_LOG_ONLY | REF_NO_DEREF; + update->flags &= ~REF_HAVE_OLD; + + /* + * Add the referent. This insertion is O(N) in the transaction + * size, but it happens at most once per symref in a + * transaction. Make sure to add new_update->refname, which will + * be valid as long as affected_refnames is in use, and NOT + * referent, which might soon be freed by our caller. + */ + item = string_list_insert(affected_refnames, new_update->refname); + if (item->util) + BUG("%s unexpectedly found in affected_refnames", + new_update->refname); + item->util = new_update; + + return 0; +} + +/* + * Return the refname under which update was originally requested. + */ +static const char *original_update_refname(struct ref_update *update) +{ + while (update->parent_update) + update = update->parent_update; + + return update->refname; +} + +/* + * Check whether the REF_HAVE_OLD and old_oid values stored in update + * are consistent with oid, which is the reference's current value. If + * everything is OK, return 0; otherwise, write an error message to + * err and return -1. + */ +static int check_old_oid(struct ref_update *update, struct object_id *oid, + struct strbuf *err) +{ + if (!(update->flags & REF_HAVE_OLD) || + oideq(oid, &update->old_oid)) + return 0; + + if (is_null_oid(&update->old_oid)) + strbuf_addf(err, "cannot lock ref '%s': " + "reference already exists", + original_update_refname(update)); + else if (is_null_oid(oid)) + strbuf_addf(err, "cannot lock ref '%s': " + "reference is missing but expected %s", + original_update_refname(update), + oid_to_hex(&update->old_oid)); + else + strbuf_addf(err, "cannot lock ref '%s': " + "is at %s but expected %s", + original_update_refname(update), + oid_to_hex(oid), + oid_to_hex(&update->old_oid)); + + return -1; +} + +/* + * Prepare for carrying out update: + * - Lock the reference referred to by update. + * - Read the reference under lock. + * - Check that its old OID value (if specified) is correct, and in + * any case record it in update->lock->old_oid for later use when + * writing the reflog. + * - If it is a symref update without REF_NO_DEREF, split it up into a + * REF_LOG_ONLY update of the symref and add a separate update for + * the referent to transaction. + * - If it is an update of head_ref, add a corresponding REF_LOG_ONLY + * update of HEAD. + */ +static int lock_ref_for_update(struct files_ref_store *refs, + struct ref_update *update, + struct ref_transaction *transaction, + const char *head_ref, + struct string_list *affected_refnames, + struct strbuf *err) +{ + struct strbuf referent = STRBUF_INIT; + int mustexist = (update->flags & REF_HAVE_OLD) && + !is_null_oid(&update->old_oid); + int ret = 0; + struct ref_lock *lock; + + files_assert_main_repository(refs, "lock_ref_for_update"); + + if ((update->flags & REF_HAVE_NEW) && is_null_oid(&update->new_oid)) + update->flags |= REF_DELETING; + + if (head_ref) { + ret = split_head_update(update, transaction, head_ref, + affected_refnames, err); + if (ret) + goto out; + } + + ret = lock_raw_ref(refs, update->refname, mustexist, + affected_refnames, + &lock, &referent, + &update->type, err); + if (ret) { + char *reason; + + reason = strbuf_detach(err, NULL); + strbuf_addf(err, "cannot lock ref '%s': %s", + original_update_refname(update), reason); + free(reason); + goto out; + } + + update->backend_data = lock; + + if (update->type & REF_ISSYMREF) { + if (update->flags & REF_NO_DEREF) { + /* + * We won't be reading the referent as part of + * the transaction, so we have to read it here + * to record and possibly check old_oid: + */ + if (!refs_resolve_ref_unsafe(&refs->base, + referent.buf, 0, + &lock->old_oid, NULL)) { + if (update->flags & REF_HAVE_OLD) { + strbuf_addf(err, "cannot lock ref '%s': " + "error reading reference", + original_update_refname(update)); + ret = TRANSACTION_GENERIC_ERROR; + goto out; + } + } else if (check_old_oid(update, &lock->old_oid, err)) { + ret = TRANSACTION_GENERIC_ERROR; + goto out; + } + } else { + /* + * Create a new update for the reference this + * symref is pointing at. Also, we will record + * and verify old_oid for this update as part + * of processing the split-off update, so we + * don't have to do it here. + */ + ret = split_symref_update(update, + referent.buf, transaction, + affected_refnames, err); + if (ret) + goto out; + } + } else { + struct ref_update *parent_update; + + if (check_old_oid(update, &lock->old_oid, err)) { + ret = TRANSACTION_GENERIC_ERROR; + goto out; + } + + /* + * If this update is happening indirectly because of a + * symref update, record the old OID in the parent + * update: + */ + for (parent_update = update->parent_update; + parent_update; + parent_update = parent_update->parent_update) { + struct ref_lock *parent_lock = parent_update->backend_data; + oidcpy(&parent_lock->old_oid, &lock->old_oid); + } + } + + if ((update->flags & REF_HAVE_NEW) && + !(update->flags & REF_DELETING) && + !(update->flags & REF_LOG_ONLY)) { + if (!(update->type & REF_ISSYMREF) && + oideq(&lock->old_oid, &update->new_oid)) { + /* + * The reference already has the desired + * value, so we don't need to write it. + */ + } else if (write_ref_to_lockfile( + lock, &update->new_oid, + update->flags & REF_SKIP_OID_VERIFICATION, + err)) { + char *write_err = strbuf_detach(err, NULL); + + /* + * The lock was freed upon failure of + * write_ref_to_lockfile(): + */ + update->backend_data = NULL; + strbuf_addf(err, + "cannot update ref '%s': %s", + update->refname, write_err); + free(write_err); + ret = TRANSACTION_GENERIC_ERROR; + goto out; + } else { + update->flags |= REF_NEEDS_COMMIT; + } + } + if (!(update->flags & REF_NEEDS_COMMIT)) { + /* + * We didn't call write_ref_to_lockfile(), so + * the lockfile is still open. Close it to + * free up the file descriptor: + */ + if (close_ref_gently(lock)) { + strbuf_addf(err, "couldn't close '%s.lock'", + update->refname); + ret = TRANSACTION_GENERIC_ERROR; + goto out; + } + } + +out: + strbuf_release(&referent); + return ret; +} + +struct files_transaction_backend_data { + struct ref_transaction *packed_transaction; + int packed_refs_locked; +}; + +/* + * Unlock any references in `transaction` that are still locked, and + * mark the transaction closed. + */ +static void files_transaction_cleanup(struct files_ref_store *refs, + struct ref_transaction *transaction) +{ + size_t i; + struct files_transaction_backend_data *backend_data = + transaction->backend_data; + struct strbuf err = STRBUF_INIT; + + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; + struct ref_lock *lock = update->backend_data; + + if (lock) { + unlock_ref(lock); + update->backend_data = NULL; + } + } + + if (backend_data) { + if (backend_data->packed_transaction && + ref_transaction_abort(backend_data->packed_transaction, &err)) { + error("error aborting transaction: %s", err.buf); + strbuf_release(&err); + } + + if (backend_data->packed_refs_locked) + packed_refs_unlock(refs->packed_ref_store); + + free(backend_data); + } + + transaction->state = REF_TRANSACTION_CLOSED; +} + +static int files_transaction_prepare(struct ref_store *ref_store, + struct ref_transaction *transaction, + struct strbuf *err) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_WRITE, + "ref_transaction_prepare"); + size_t i; + int ret = 0; + struct string_list affected_refnames = STRING_LIST_INIT_NODUP; + char *head_ref = NULL; + int head_type; + struct files_transaction_backend_data *backend_data; + struct ref_transaction *packed_transaction = NULL; + + assert(err); + + if (!transaction->nr) + goto cleanup; + + CALLOC_ARRAY(backend_data, 1); + transaction->backend_data = backend_data; + + /* + * Fail if a refname appears more than once in the + * transaction. (If we end up splitting up any updates using + * split_symref_update() or split_head_update(), those + * functions will check that the new updates don't have the + * same refname as any existing ones.) Also fail if any of the + * updates use REF_IS_PRUNING without REF_NO_DEREF. + */ + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; + struct string_list_item *item = + string_list_append(&affected_refnames, update->refname); + + if ((update->flags & REF_IS_PRUNING) && + !(update->flags & REF_NO_DEREF)) + BUG("REF_IS_PRUNING set without REF_NO_DEREF"); + + /* + * We store a pointer to update in item->util, but at + * the moment we never use the value of this field + * except to check whether it is non-NULL. + */ + item->util = update; + } + string_list_sort(&affected_refnames); + if (ref_update_reject_duplicates(&affected_refnames, err)) { + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + + /* + * Special hack: If a branch is updated directly and HEAD + * points to it (may happen on the remote side of a push + * for example) then logically the HEAD reflog should be + * updated too. + * + * A generic solution would require reverse symref lookups, + * but finding all symrefs pointing to a given branch would be + * rather costly for this rare event (the direct update of a + * branch) to be worth it. So let's cheat and check with HEAD + * only, which should cover 99% of all usage scenarios (even + * 100% of the default ones). + * + * So if HEAD is a symbolic reference, then record the name of + * the reference that it points to. If we see an update of + * head_ref within the transaction, then split_head_update() + * arranges for the reflog of HEAD to be updated, too. + */ + head_ref = refs_resolve_refdup(ref_store, "HEAD", + RESOLVE_REF_NO_RECURSE, + NULL, &head_type); + + if (head_ref && !(head_type & REF_ISSYMREF)) { + FREE_AND_NULL(head_ref); + } + + /* + * Acquire all locks, verify old values if provided, check + * that new values are valid, and write new values to the + * lockfiles, ready to be activated. Only keep one lockfile + * open at a time to avoid running out of file descriptors. + * Note that lock_ref_for_update() might append more updates + * to the transaction. + */ + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; + + ret = lock_ref_for_update(refs, update, transaction, + head_ref, &affected_refnames, err); + if (ret) + goto cleanup; + + if (update->flags & REF_DELETING && + !(update->flags & REF_LOG_ONLY) && + !(update->flags & REF_IS_PRUNING)) { + /* + * This reference has to be deleted from + * packed-refs if it exists there. + */ + if (!packed_transaction) { + packed_transaction = ref_store_transaction_begin( + refs->packed_ref_store, err); + if (!packed_transaction) { + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + + backend_data->packed_transaction = + packed_transaction; + } + + ref_transaction_add_update( + packed_transaction, update->refname, + REF_HAVE_NEW | REF_NO_DEREF, + &update->new_oid, NULL, + NULL); + } + } + + if (packed_transaction) { + if (packed_refs_lock(refs->packed_ref_store, 0, err)) { + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + backend_data->packed_refs_locked = 1; + + if (is_packed_transaction_needed(refs->packed_ref_store, + packed_transaction)) { + ret = ref_transaction_prepare(packed_transaction, err); + /* + * A failure during the prepare step will abort + * itself, but not free. Do that now, and disconnect + * from the files_transaction so it does not try to + * abort us when we hit the cleanup code below. + */ + if (ret) { + ref_transaction_free(packed_transaction); + backend_data->packed_transaction = NULL; + } + } else { + /* + * We can skip rewriting the `packed-refs` + * file. But we do need to leave it locked, so + * that somebody else doesn't pack a reference + * that we are trying to delete. + * + * We need to disconnect our transaction from + * backend_data, since the abort (whether successful or + * not) will free it. + */ + backend_data->packed_transaction = NULL; + if (ref_transaction_abort(packed_transaction, err)) { + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + } + } + +cleanup: + free(head_ref); + string_list_clear(&affected_refnames, 0); + + if (ret) + files_transaction_cleanup(refs, transaction); + else + transaction->state = REF_TRANSACTION_PREPARED; + + return ret; +} + +static int files_transaction_finish(struct ref_store *ref_store, + struct ref_transaction *transaction, + struct strbuf *err) +{ + struct files_ref_store *refs = + files_downcast(ref_store, 0, "ref_transaction_finish"); + size_t i; + int ret = 0; + struct strbuf sb = STRBUF_INIT; + struct files_transaction_backend_data *backend_data; + struct ref_transaction *packed_transaction; + + + assert(err); + + if (!transaction->nr) { + transaction->state = REF_TRANSACTION_CLOSED; + return 0; + } + + backend_data = transaction->backend_data; + packed_transaction = backend_data->packed_transaction; + + /* Perform updates first so live commits remain referenced */ + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; + struct ref_lock *lock = update->backend_data; + + if (update->flags & REF_NEEDS_COMMIT || + update->flags & REF_LOG_ONLY) { + if (files_log_ref_write(refs, + lock->ref_name, + &lock->old_oid, + &update->new_oid, + update->msg, update->flags, + err)) { + char *old_msg = strbuf_detach(err, NULL); + + strbuf_addf(err, "cannot update the ref '%s': %s", + lock->ref_name, old_msg); + free(old_msg); + unlock_ref(lock); + update->backend_data = NULL; + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + } + if (update->flags & REF_NEEDS_COMMIT) { + clear_loose_ref_cache(refs); + if (commit_ref(lock)) { + strbuf_addf(err, "couldn't set '%s'", lock->ref_name); + unlock_ref(lock); + update->backend_data = NULL; + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + } + } + + /* + * Now that updates are safely completed, we can perform + * deletes. First delete the reflogs of any references that + * will be deleted, since (in the unexpected event of an + * error) leaving a reference without a reflog is less bad + * than leaving a reflog without a reference (the latter is a + * mildly invalid repository state): + */ + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; + if (update->flags & REF_DELETING && + !(update->flags & REF_LOG_ONLY) && + !(update->flags & REF_IS_PRUNING)) { + strbuf_reset(&sb); + files_reflog_path(refs, &sb, update->refname); + if (!unlink_or_warn(sb.buf)) + try_remove_empty_parents(refs, update->refname, + REMOVE_EMPTY_PARENTS_REFLOG); + } + } + + /* + * Perform deletes now that updates are safely completed. + * + * First delete any packed versions of the references, while + * retaining the packed-refs lock: + */ + if (packed_transaction) { + ret = ref_transaction_commit(packed_transaction, err); + ref_transaction_free(packed_transaction); + packed_transaction = NULL; + backend_data->packed_transaction = NULL; + if (ret) + goto cleanup; + } + + /* Now delete the loose versions of the references: */ + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; + struct ref_lock *lock = update->backend_data; + + if (update->flags & REF_DELETING && + !(update->flags & REF_LOG_ONLY)) { + update->flags |= REF_DELETED_RMDIR; + if (!(update->type & REF_ISPACKED) || + update->type & REF_ISSYMREF) { + /* It is a loose reference. */ + strbuf_reset(&sb); + files_ref_path(refs, &sb, lock->ref_name); + if (unlink_or_msg(sb.buf, err)) { + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + } + } + } + + clear_loose_ref_cache(refs); + +cleanup: + files_transaction_cleanup(refs, transaction); + + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; + + if (update->flags & REF_DELETED_RMDIR) { + /* + * The reference was deleted. Delete any + * empty parent directories. (Note that this + * can only work because we have already + * removed the lockfile.) + */ + try_remove_empty_parents(refs, update->refname, + REMOVE_EMPTY_PARENTS_REF); + } + } + + strbuf_release(&sb); + return ret; +} + +static int files_transaction_abort(struct ref_store *ref_store, + struct ref_transaction *transaction, + struct strbuf *err UNUSED) +{ + struct files_ref_store *refs = + files_downcast(ref_store, 0, "ref_transaction_abort"); + + files_transaction_cleanup(refs, transaction); + return 0; +} + +static int ref_present(const char *refname, + const struct object_id *oid UNUSED, + int flags UNUSED, + void *cb_data) +{ + struct string_list *affected_refnames = cb_data; + + return string_list_has_string(affected_refnames, refname); +} + +static int files_initial_transaction_commit(struct ref_store *ref_store, + struct ref_transaction *transaction, + struct strbuf *err) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_WRITE, + "initial_ref_transaction_commit"); + size_t i; + int ret = 0; + struct string_list affected_refnames = STRING_LIST_INIT_NODUP; + struct ref_transaction *packed_transaction = NULL; + + assert(err); + + if (transaction->state != REF_TRANSACTION_OPEN) + BUG("commit called for transaction that is not open"); + + /* Fail if a refname appears more than once in the transaction: */ + for (i = 0; i < transaction->nr; i++) + string_list_append(&affected_refnames, + transaction->updates[i]->refname); + string_list_sort(&affected_refnames); + if (ref_update_reject_duplicates(&affected_refnames, err)) { + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + + /* + * It's really undefined to call this function in an active + * repository or when there are existing references: we are + * only locking and changing packed-refs, so (1) any + * simultaneous processes might try to change a reference at + * the same time we do, and (2) any existing loose versions of + * the references that we are setting would have precedence + * over our values. But some remote helpers create the remote + * "HEAD" and "master" branches before calling this function, + * so here we really only check that none of the references + * that we are creating already exists. + */ + if (refs_for_each_rawref(&refs->base, ref_present, + &affected_refnames)) + BUG("initial ref transaction called with existing refs"); + + packed_transaction = ref_store_transaction_begin(refs->packed_ref_store, err); + if (!packed_transaction) { + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; + + if ((update->flags & REF_HAVE_OLD) && + !is_null_oid(&update->old_oid)) + BUG("initial ref transaction with old_sha1 set"); + if (refs_verify_refname_available(&refs->base, update->refname, + &affected_refnames, NULL, + err)) { + ret = TRANSACTION_NAME_CONFLICT; + goto cleanup; + } + + /* + * Add a reference creation for this reference to the + * packed-refs transaction: + */ + ref_transaction_add_update(packed_transaction, update->refname, + update->flags & ~REF_HAVE_OLD, + &update->new_oid, &update->old_oid, + NULL); + } + + if (packed_refs_lock(refs->packed_ref_store, 0, err)) { + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + + if (initial_ref_transaction_commit(packed_transaction, err)) { + ret = TRANSACTION_GENERIC_ERROR; + } + + packed_refs_unlock(refs->packed_ref_store); +cleanup: + if (packed_transaction) + ref_transaction_free(packed_transaction); + transaction->state = REF_TRANSACTION_CLOSED; + string_list_clear(&affected_refnames, 0); + return ret; +} + +struct expire_reflog_cb { + reflog_expiry_should_prune_fn *should_prune_fn; + void *policy_cb; + FILE *newlog; + struct object_id last_kept_oid; + unsigned int rewrite:1, + dry_run:1; +}; + +static int expire_reflog_ent(struct object_id *ooid, struct object_id *noid, + const char *email, timestamp_t timestamp, int tz, + const char *message, void *cb_data) +{ + struct expire_reflog_cb *cb = cb_data; + reflog_expiry_should_prune_fn *fn = cb->should_prune_fn; + + if (cb->rewrite) + ooid = &cb->last_kept_oid; + + if (fn(ooid, noid, email, timestamp, tz, message, cb->policy_cb)) + return 0; + + if (cb->dry_run) + return 0; /* --dry-run */ + + fprintf(cb->newlog, "%s %s %s %"PRItime" %+05d\t%s", oid_to_hex(ooid), + oid_to_hex(noid), email, timestamp, tz, message); + oidcpy(&cb->last_kept_oid, noid); + + return 0; +} + +static int files_reflog_expire(struct ref_store *ref_store, + const char *refname, + unsigned int expire_flags, + reflog_expiry_prepare_fn prepare_fn, + reflog_expiry_should_prune_fn should_prune_fn, + reflog_expiry_cleanup_fn cleanup_fn, + void *policy_cb_data) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_WRITE, "reflog_expire"); + struct lock_file reflog_lock = LOCK_INIT; + struct expire_reflog_cb cb; + struct ref_lock *lock; + struct strbuf log_file_sb = STRBUF_INIT; + char *log_file; + int status = 0; + struct strbuf err = STRBUF_INIT; + const struct object_id *oid; + + memset(&cb, 0, sizeof(cb)); + cb.rewrite = !!(expire_flags & EXPIRE_REFLOGS_REWRITE); + cb.dry_run = !!(expire_flags & EXPIRE_REFLOGS_DRY_RUN); + cb.policy_cb = policy_cb_data; + cb.should_prune_fn = should_prune_fn; + + /* + * The reflog file is locked by holding the lock on the + * reference itself, plus we might need to update the + * reference if --updateref was specified: + */ + lock = lock_ref_oid_basic(refs, refname, &err); + if (!lock) { + error("cannot lock ref '%s': %s", refname, err.buf); + strbuf_release(&err); + return -1; + } + oid = &lock->old_oid; + + /* + * When refs are deleted, their reflog is deleted before the + * ref itself is deleted. This is because there is no separate + * lock for reflog; instead we take a lock on the ref with + * lock_ref_oid_basic(). + * + * If a race happens and the reflog doesn't exist after we've + * acquired the lock that's OK. We've got nothing more to do; + * We were asked to delete the reflog, but someone else + * deleted it! The caller doesn't care that we deleted it, + * just that it is deleted. So we can return successfully. + */ + if (!refs_reflog_exists(ref_store, refname)) { + unlock_ref(lock); + return 0; + } + + files_reflog_path(refs, &log_file_sb, refname); + log_file = strbuf_detach(&log_file_sb, NULL); + if (!cb.dry_run) { + /* + * Even though holding $GIT_DIR/logs/$reflog.lock has + * no locking implications, we use the lock_file + * machinery here anyway because it does a lot of the + * work we need, including cleaning up if the program + * exits unexpectedly. + */ + if (hold_lock_file_for_update(&reflog_lock, log_file, 0) < 0) { + struct strbuf err = STRBUF_INIT; + unable_to_lock_message(log_file, errno, &err); + error("%s", err.buf); + strbuf_release(&err); + goto failure; + } + cb.newlog = fdopen_lock_file(&reflog_lock, "w"); + if (!cb.newlog) { + error("cannot fdopen %s (%s)", + get_lock_file_path(&reflog_lock), strerror(errno)); + goto failure; + } + } + + (*prepare_fn)(refname, oid, cb.policy_cb); + refs_for_each_reflog_ent(ref_store, refname, expire_reflog_ent, &cb); + (*cleanup_fn)(cb.policy_cb); + + if (!cb.dry_run) { + /* + * It doesn't make sense to adjust a reference pointed + * to by a symbolic ref based on expiring entries in + * the symbolic reference's reflog. Nor can we update + * a reference if there are no remaining reflog + * entries. + */ + int update = 0; + + if ((expire_flags & EXPIRE_REFLOGS_UPDATE_REF) && + !is_null_oid(&cb.last_kept_oid)) { + int type; + const char *ref; + + ref = refs_resolve_ref_unsafe(&refs->base, refname, + RESOLVE_REF_NO_RECURSE, + NULL, &type); + update = !!(ref && !(type & REF_ISSYMREF)); + } + + if (close_lock_file_gently(&reflog_lock)) { + status |= error("couldn't write %s: %s", log_file, + strerror(errno)); + rollback_lock_file(&reflog_lock); + } else if (update && + (write_in_full(get_lock_file_fd(&lock->lk), + oid_to_hex(&cb.last_kept_oid), the_hash_algo->hexsz) < 0 || + write_str_in_full(get_lock_file_fd(&lock->lk), "\n") < 0 || + close_ref_gently(lock) < 0)) { + status |= error("couldn't write %s", + get_lock_file_path(&lock->lk)); + rollback_lock_file(&reflog_lock); + } else if (commit_lock_file(&reflog_lock)) { + status |= error("unable to write reflog '%s' (%s)", + log_file, strerror(errno)); + } else if (update && commit_ref(lock)) { + status |= error("couldn't set %s", lock->ref_name); + } + } + free(log_file); + unlock_ref(lock); + return status; + + failure: + rollback_lock_file(&reflog_lock); + free(log_file); + unlock_ref(lock); + return -1; +} + +static int files_init_db(struct ref_store *ref_store, struct strbuf *err UNUSED) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_WRITE, "init_db"); + struct strbuf sb = STRBUF_INIT; + + /* + * Create .git/refs/{heads,tags} + */ + files_ref_path(refs, &sb, "refs/heads"); + safe_create_dir(sb.buf, 1); + + strbuf_reset(&sb); + files_ref_path(refs, &sb, "refs/tags"); + safe_create_dir(sb.buf, 1); + + strbuf_release(&sb); + return 0; +} + +struct ref_storage_be refs_be_files = { + .next = NULL, + .name = "files", + .init = files_ref_store_create, + .init_db = files_init_db, + .transaction_prepare = files_transaction_prepare, + .transaction_finish = files_transaction_finish, + .transaction_abort = files_transaction_abort, + .initial_transaction_commit = files_initial_transaction_commit, + + .pack_refs = files_pack_refs, + .create_symref = files_create_symref, + .delete_refs = files_delete_refs, + .rename_ref = files_rename_ref, + .copy_ref = files_copy_ref, + + .iterator_begin = files_ref_iterator_begin, + .read_raw_ref = files_read_raw_ref, + .read_symbolic_ref = files_read_symbolic_ref, + + .reflog_iterator_begin = files_reflog_iterator_begin, + .for_each_reflog_ent = files_for_each_reflog_ent, + .for_each_reflog_ent_reverse = files_for_each_reflog_ent_reverse, + .reflog_exists = files_reflog_exists, + .create_reflog = files_create_reflog, + .delete_reflog = files_delete_reflog, + .reflog_expire = files_reflog_expire +}; diff --git a/refs/iterator.c b/refs/iterator.c new file mode 100644 index 0000000..c9fd0bc --- /dev/null +++ b/refs/iterator.c @@ -0,0 +1,435 @@ +/* + * Generic reference iterator infrastructure. See refs-internal.h for + * documentation about the design and use of reference iterators. + */ + +#include "cache.h" +#include "refs.h" +#include "refs/refs-internal.h" +#include "iterator.h" + +int ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + return ref_iterator->vtable->advance(ref_iterator); +} + +int ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) +{ + return ref_iterator->vtable->peel(ref_iterator, peeled); +} + +int ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + return ref_iterator->vtable->abort(ref_iterator); +} + +void base_ref_iterator_init(struct ref_iterator *iter, + struct ref_iterator_vtable *vtable, + int ordered) +{ + iter->vtable = vtable; + iter->ordered = !!ordered; + iter->refname = NULL; + iter->oid = NULL; + iter->flags = 0; +} + +void base_ref_iterator_free(struct ref_iterator *iter) +{ + /* Help make use-after-free bugs fail quickly: */ + iter->vtable = NULL; + free(iter); +} + +struct empty_ref_iterator { + struct ref_iterator base; +}; + +static int empty_ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + return ref_iterator_abort(ref_iterator); +} + +static int empty_ref_iterator_peel(struct ref_iterator *ref_iterator UNUSED, + struct object_id *peeled UNUSED) +{ + BUG("peel called for empty iterator"); +} + +static int empty_ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + base_ref_iterator_free(ref_iterator); + return ITER_DONE; +} + +static struct ref_iterator_vtable empty_ref_iterator_vtable = { + .advance = empty_ref_iterator_advance, + .peel = empty_ref_iterator_peel, + .abort = empty_ref_iterator_abort, +}; + +struct ref_iterator *empty_ref_iterator_begin(void) +{ + struct empty_ref_iterator *iter = xcalloc(1, sizeof(*iter)); + struct ref_iterator *ref_iterator = &iter->base; + + base_ref_iterator_init(ref_iterator, &empty_ref_iterator_vtable, 1); + return ref_iterator; +} + +int is_empty_ref_iterator(struct ref_iterator *ref_iterator) +{ + return ref_iterator->vtable == &empty_ref_iterator_vtable; +} + +struct merge_ref_iterator { + struct ref_iterator base; + + struct ref_iterator *iter0, *iter1; + + ref_iterator_select_fn *select; + void *cb_data; + + /* + * A pointer to iter0 or iter1 (whichever is supplying the + * current value), or NULL if advance has not yet been called. + */ + struct ref_iterator **current; +}; + +static int merge_ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + struct merge_ref_iterator *iter = + (struct merge_ref_iterator *)ref_iterator; + int ok; + + if (!iter->current) { + /* Initialize: advance both iterators to their first entries */ + if ((ok = ref_iterator_advance(iter->iter0)) != ITER_OK) { + iter->iter0 = NULL; + if (ok == ITER_ERROR) + goto error; + } + if ((ok = ref_iterator_advance(iter->iter1)) != ITER_OK) { + iter->iter1 = NULL; + if (ok == ITER_ERROR) + goto error; + } + } else { + /* + * Advance the current iterator past the just-used + * entry: + */ + if ((ok = ref_iterator_advance(*iter->current)) != ITER_OK) { + *iter->current = NULL; + if (ok == ITER_ERROR) + goto error; + } + } + + /* Loop until we find an entry that we can yield. */ + while (1) { + struct ref_iterator **secondary; + enum iterator_selection selection = + iter->select(iter->iter0, iter->iter1, iter->cb_data); + + if (selection == ITER_SELECT_DONE) { + return ref_iterator_abort(ref_iterator); + } else if (selection == ITER_SELECT_ERROR) { + ref_iterator_abort(ref_iterator); + return ITER_ERROR; + } + + if ((selection & ITER_CURRENT_SELECTION_MASK) == 0) { + iter->current = &iter->iter0; + secondary = &iter->iter1; + } else { + iter->current = &iter->iter1; + secondary = &iter->iter0; + } + + if (selection & ITER_SKIP_SECONDARY) { + if ((ok = ref_iterator_advance(*secondary)) != ITER_OK) { + *secondary = NULL; + if (ok == ITER_ERROR) + goto error; + } + } + + if (selection & ITER_YIELD_CURRENT) { + iter->base.refname = (*iter->current)->refname; + iter->base.oid = (*iter->current)->oid; + iter->base.flags = (*iter->current)->flags; + return ITER_OK; + } + } + +error: + ref_iterator_abort(ref_iterator); + return ITER_ERROR; +} + +static int merge_ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) +{ + struct merge_ref_iterator *iter = + (struct merge_ref_iterator *)ref_iterator; + + if (!iter->current) { + BUG("peel called before advance for merge iterator"); + } + return ref_iterator_peel(*iter->current, peeled); +} + +static int merge_ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + struct merge_ref_iterator *iter = + (struct merge_ref_iterator *)ref_iterator; + int ok = ITER_DONE; + + if (iter->iter0) { + if (ref_iterator_abort(iter->iter0) != ITER_DONE) + ok = ITER_ERROR; + } + if (iter->iter1) { + if (ref_iterator_abort(iter->iter1) != ITER_DONE) + ok = ITER_ERROR; + } + base_ref_iterator_free(ref_iterator); + return ok; +} + +static struct ref_iterator_vtable merge_ref_iterator_vtable = { + .advance = merge_ref_iterator_advance, + .peel = merge_ref_iterator_peel, + .abort = merge_ref_iterator_abort, +}; + +struct ref_iterator *merge_ref_iterator_begin( + int ordered, + struct ref_iterator *iter0, struct ref_iterator *iter1, + ref_iterator_select_fn *select, void *cb_data) +{ + struct merge_ref_iterator *iter = xcalloc(1, sizeof(*iter)); + struct ref_iterator *ref_iterator = &iter->base; + + /* + * We can't do the same kind of is_empty_ref_iterator()-style + * optimization here as overlay_ref_iterator_begin() does, + * because we don't know the semantics of the select function. + * It might, for example, implement "intersect" by passing + * references through only if they exist in both iterators. + */ + + base_ref_iterator_init(ref_iterator, &merge_ref_iterator_vtable, ordered); + iter->iter0 = iter0; + iter->iter1 = iter1; + iter->select = select; + iter->cb_data = cb_data; + iter->current = NULL; + return ref_iterator; +} + +/* + * A ref_iterator_select_fn that overlays the items from front on top + * of those from back (like loose refs over packed refs). See + * overlay_ref_iterator_begin(). + */ +static enum iterator_selection overlay_iterator_select( + struct ref_iterator *front, struct ref_iterator *back, + void *cb_data UNUSED) +{ + int cmp; + + if (!back) + return front ? ITER_SELECT_0 : ITER_SELECT_DONE; + else if (!front) + return ITER_SELECT_1; + + cmp = strcmp(front->refname, back->refname); + + if (cmp < 0) + return ITER_SELECT_0; + else if (cmp > 0) + return ITER_SELECT_1; + else + return ITER_SELECT_0_SKIP_1; +} + +struct ref_iterator *overlay_ref_iterator_begin( + struct ref_iterator *front, struct ref_iterator *back) +{ + /* + * Optimization: if one of the iterators is empty, return the + * other one rather than incurring the overhead of wrapping + * them. + */ + if (is_empty_ref_iterator(front)) { + ref_iterator_abort(front); + return back; + } else if (is_empty_ref_iterator(back)) { + ref_iterator_abort(back); + return front; + } else if (!front->ordered || !back->ordered) { + BUG("overlay_ref_iterator requires ordered inputs"); + } + + return merge_ref_iterator_begin(1, front, back, + overlay_iterator_select, NULL); +} + +struct prefix_ref_iterator { + struct ref_iterator base; + + struct ref_iterator *iter0; + char *prefix; + int trim; +}; + +/* Return -1, 0, 1 if refname is before, inside, or after the prefix. */ +static int compare_prefix(const char *refname, const char *prefix) +{ + while (*prefix) { + if (*refname != *prefix) + return ((unsigned char)*refname < (unsigned char)*prefix) ? -1 : +1; + + refname++; + prefix++; + } + + return 0; +} + +static int prefix_ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + struct prefix_ref_iterator *iter = + (struct prefix_ref_iterator *)ref_iterator; + int ok; + + while ((ok = ref_iterator_advance(iter->iter0)) == ITER_OK) { + int cmp = compare_prefix(iter->iter0->refname, iter->prefix); + + if (cmp < 0) + continue; + + if (cmp > 0) { + /* + * If the source iterator is ordered, then we + * can stop the iteration as soon as we see a + * refname that comes after the prefix: + */ + if (iter->iter0->ordered) { + ok = ref_iterator_abort(iter->iter0); + break; + } else { + continue; + } + } + + if (iter->trim) { + /* + * It is nonsense to trim off characters that + * you haven't already checked for via a + * prefix check, whether via this + * `prefix_ref_iterator` or upstream in + * `iter0`). So if there wouldn't be at least + * one character left in the refname after + * trimming, report it as a bug: + */ + if (strlen(iter->iter0->refname) <= iter->trim) + BUG("attempt to trim too many characters"); + iter->base.refname = iter->iter0->refname + iter->trim; + } else { + iter->base.refname = iter->iter0->refname; + } + + iter->base.oid = iter->iter0->oid; + iter->base.flags = iter->iter0->flags; + return ITER_OK; + } + + iter->iter0 = NULL; + if (ref_iterator_abort(ref_iterator) != ITER_DONE) + return ITER_ERROR; + return ok; +} + +static int prefix_ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) +{ + struct prefix_ref_iterator *iter = + (struct prefix_ref_iterator *)ref_iterator; + + return ref_iterator_peel(iter->iter0, peeled); +} + +static int prefix_ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + struct prefix_ref_iterator *iter = + (struct prefix_ref_iterator *)ref_iterator; + int ok = ITER_DONE; + + if (iter->iter0) + ok = ref_iterator_abort(iter->iter0); + free(iter->prefix); + base_ref_iterator_free(ref_iterator); + return ok; +} + +static struct ref_iterator_vtable prefix_ref_iterator_vtable = { + .advance = prefix_ref_iterator_advance, + .peel = prefix_ref_iterator_peel, + .abort = prefix_ref_iterator_abort, +}; + +struct ref_iterator *prefix_ref_iterator_begin(struct ref_iterator *iter0, + const char *prefix, + int trim) +{ + struct prefix_ref_iterator *iter; + struct ref_iterator *ref_iterator; + + if (!*prefix && !trim) + return iter0; /* optimization: no need to wrap iterator */ + + CALLOC_ARRAY(iter, 1); + ref_iterator = &iter->base; + + base_ref_iterator_init(ref_iterator, &prefix_ref_iterator_vtable, iter0->ordered); + + iter->iter0 = iter0; + iter->prefix = xstrdup(prefix); + iter->trim = trim; + + return ref_iterator; +} + +struct ref_iterator *current_ref_iter = NULL; + +int do_for_each_repo_ref_iterator(struct repository *r, struct ref_iterator *iter, + each_repo_ref_fn fn, void *cb_data) +{ + int retval = 0, ok; + struct ref_iterator *old_ref_iter = current_ref_iter; + + current_ref_iter = iter; + while ((ok = ref_iterator_advance(iter)) == ITER_OK) { + retval = fn(r, iter->refname, iter->oid, iter->flags, cb_data); + if (retval) { + /* + * If ref_iterator_abort() returns ITER_ERROR, + * we ignore that error in deference to the + * callback function's return value. + */ + ref_iterator_abort(iter); + goto out; + } + } + +out: + current_ref_iter = old_ref_iter; + if (ok == ITER_ERROR) + return -1; + return retval; +} diff --git a/refs/packed-backend.c b/refs/packed-backend.c new file mode 100644 index 0000000..c1c71d1 --- /dev/null +++ b/refs/packed-backend.c @@ -0,0 +1,1615 @@ +#include "../cache.h" +#include "../config.h" +#include "../refs.h" +#include "refs-internal.h" +#include "packed-backend.h" +#include "../iterator.h" +#include "../lockfile.h" +#include "../chdir-notify.h" + +enum mmap_strategy { + /* + * Don't use mmap() at all for reading `packed-refs`. + */ + MMAP_NONE, + + /* + * Can use mmap() for reading `packed-refs`, but the file must + * not remain mmapped. This is the usual option on Windows, + * where you cannot rename a new version of a file onto a file + * that is currently mmapped. + */ + MMAP_TEMPORARY, + + /* + * It is OK to leave the `packed-refs` file mmapped while + * arbitrary other code is running. + */ + MMAP_OK +}; + +#if defined(NO_MMAP) +static enum mmap_strategy mmap_strategy = MMAP_NONE; +#elif defined(MMAP_PREVENTS_DELETE) +static enum mmap_strategy mmap_strategy = MMAP_TEMPORARY; +#else +static enum mmap_strategy mmap_strategy = MMAP_OK; +#endif + +struct packed_ref_store; + +/* + * A `snapshot` represents one snapshot of a `packed-refs` file. + * + * Normally, this will be a mmapped view of the contents of the + * `packed-refs` file at the time the snapshot was created. However, + * if the `packed-refs` file was not sorted, this might point at heap + * memory holding the contents of the `packed-refs` file with its + * records sorted by refname. + * + * `snapshot` instances are reference counted (via + * `acquire_snapshot()` and `release_snapshot()`). This is to prevent + * an instance from disappearing while an iterator is still iterating + * over it. Instances are garbage collected when their `referrers` + * count goes to zero. + * + * The most recent `snapshot`, if available, is referenced by the + * `packed_ref_store`. Its freshness is checked whenever + * `get_snapshot()` is called; if the existing snapshot is obsolete, a + * new snapshot is taken. + */ +struct snapshot { + /* + * A back-pointer to the packed_ref_store with which this + * snapshot is associated: + */ + struct packed_ref_store *refs; + + /* Is the `packed-refs` file currently mmapped? */ + int mmapped; + + /* + * The contents of the `packed-refs` file: + * + * - buf -- a pointer to the start of the memory + * - start -- a pointer to the first byte of actual references + * (i.e., after the header line, if one is present) + * - eof -- a pointer just past the end of the reference + * contents + * + * If the `packed-refs` file was already sorted, `buf` points + * at the mmapped contents of the file. If not, it points at + * heap-allocated memory containing the contents, sorted. If + * there were no contents (e.g., because the file didn't + * exist), `buf`, `start`, and `eof` are all NULL. + */ + char *buf, *start, *eof; + + /* + * What is the peeled state of the `packed-refs` file that + * this snapshot represents? (This is usually determined from + * the file's header.) + */ + enum { PEELED_NONE, PEELED_TAGS, PEELED_FULLY } peeled; + + /* + * Count of references to this instance, including the pointer + * from `packed_ref_store::snapshot`, if any. The instance + * will not be freed as long as the reference count is + * nonzero. + */ + unsigned int referrers; + + /* + * The metadata of the `packed-refs` file from which this + * snapshot was created, used to tell if the file has been + * replaced since we read it. + */ + struct stat_validity validity; +}; + +/* + * A `ref_store` representing references stored in a `packed-refs` + * file. It implements the `ref_store` interface, though it has some + * limitations: + * + * - It cannot store symbolic references. + * + * - It cannot store reflogs. + * + * - It does not support reference renaming (though it could). + * + * On the other hand, it can be locked outside of a reference + * transaction. In that case, it remains locked even after the + * transaction is done and the new `packed-refs` file is activated. + */ +struct packed_ref_store { + struct ref_store base; + + unsigned int store_flags; + + /* The path of the "packed-refs" file: */ + char *path; + + /* + * A snapshot of the values read from the `packed-refs` file, + * if it might still be current; otherwise, NULL. + */ + struct snapshot *snapshot; + + /* + * Lock used for the "packed-refs" file. Note that this (and + * thus the enclosing `packed_ref_store`) must not be freed. + */ + struct lock_file lock; + + /* + * Temporary file used when rewriting new contents to the + * "packed-refs" file. Note that this (and thus the enclosing + * `packed_ref_store`) must not be freed. + */ + struct tempfile *tempfile; +}; + +/* + * Increment the reference count of `*snapshot`. + */ +static void acquire_snapshot(struct snapshot *snapshot) +{ + snapshot->referrers++; +} + +/* + * If the buffer in `snapshot` is active, then either munmap the + * memory and close the file, or free the memory. Then set the buffer + * pointers to NULL. + */ +static void clear_snapshot_buffer(struct snapshot *snapshot) +{ + if (snapshot->mmapped) { + if (munmap(snapshot->buf, snapshot->eof - snapshot->buf)) + die_errno("error ummapping packed-refs file %s", + snapshot->refs->path); + snapshot->mmapped = 0; + } else { + free(snapshot->buf); + } + snapshot->buf = snapshot->start = snapshot->eof = NULL; +} + +/* + * Decrease the reference count of `*snapshot`. If it goes to zero, + * free `*snapshot` and return true; otherwise return false. + */ +static int release_snapshot(struct snapshot *snapshot) +{ + if (!--snapshot->referrers) { + stat_validity_clear(&snapshot->validity); + clear_snapshot_buffer(snapshot); + free(snapshot); + return 1; + } else { + return 0; + } +} + +struct ref_store *packed_ref_store_create(struct repository *repo, + const char *gitdir, + unsigned int store_flags) +{ + struct packed_ref_store *refs = xcalloc(1, sizeof(*refs)); + struct ref_store *ref_store = (struct ref_store *)refs; + struct strbuf sb = STRBUF_INIT; + + base_ref_store_init(ref_store, repo, gitdir, &refs_be_packed); + refs->store_flags = store_flags; + + strbuf_addf(&sb, "%s/packed-refs", gitdir); + refs->path = strbuf_detach(&sb, NULL); + chdir_notify_reparent("packed-refs", &refs->path); + return ref_store; +} + +/* + * Downcast `ref_store` to `packed_ref_store`. Die if `ref_store` is + * not a `packed_ref_store`. Also die if `packed_ref_store` doesn't + * support at least the flags specified in `required_flags`. `caller` + * is used in any necessary error messages. + */ +static struct packed_ref_store *packed_downcast(struct ref_store *ref_store, + unsigned int required_flags, + const char *caller) +{ + struct packed_ref_store *refs; + + if (ref_store->be != &refs_be_packed) + BUG("ref_store is type \"%s\" not \"packed\" in %s", + ref_store->be->name, caller); + + refs = (struct packed_ref_store *)ref_store; + + if ((refs->store_flags & required_flags) != required_flags) + BUG("unallowed operation (%s), requires %x, has %x\n", + caller, required_flags, refs->store_flags); + + return refs; +} + +static void clear_snapshot(struct packed_ref_store *refs) +{ + if (refs->snapshot) { + struct snapshot *snapshot = refs->snapshot; + + refs->snapshot = NULL; + release_snapshot(snapshot); + } +} + +static NORETURN void die_unterminated_line(const char *path, + const char *p, size_t len) +{ + if (len < 80) + die("unterminated line in %s: %.*s", path, (int)len, p); + else + die("unterminated line in %s: %.75s...", path, p); +} + +static NORETURN void die_invalid_line(const char *path, + const char *p, size_t len) +{ + const char *eol = memchr(p, '\n', len); + + if (!eol) + die_unterminated_line(path, p, len); + else if (eol - p < 80) + die("unexpected line in %s: %.*s", path, (int)(eol - p), p); + else + die("unexpected line in %s: %.75s...", path, p); + +} + +struct snapshot_record { + const char *start; + size_t len; +}; + +static int cmp_packed_ref_records(const void *v1, const void *v2) +{ + const struct snapshot_record *e1 = v1, *e2 = v2; + const char *r1 = e1->start + the_hash_algo->hexsz + 1; + const char *r2 = e2->start + the_hash_algo->hexsz + 1; + + while (1) { + if (*r1 == '\n') + return *r2 == '\n' ? 0 : -1; + if (*r1 != *r2) { + if (*r2 == '\n') + return 1; + else + return (unsigned char)*r1 < (unsigned char)*r2 ? -1 : +1; + } + r1++; + r2++; + } +} + +/* + * Compare a snapshot record at `rec` to the specified NUL-terminated + * refname. + */ +static int cmp_record_to_refname(const char *rec, const char *refname) +{ + const char *r1 = rec + the_hash_algo->hexsz + 1; + const char *r2 = refname; + + while (1) { + if (*r1 == '\n') + return *r2 ? -1 : 0; + if (!*r2) + return 1; + if (*r1 != *r2) + return (unsigned char)*r1 < (unsigned char)*r2 ? -1 : +1; + r1++; + r2++; + } +} + +/* + * `snapshot->buf` is not known to be sorted. Check whether it is, and + * if not, sort it into new memory and munmap/free the old storage. + */ +static void sort_snapshot(struct snapshot *snapshot) +{ + struct snapshot_record *records = NULL; + size_t alloc = 0, nr = 0; + int sorted = 1; + const char *pos, *eof, *eol; + size_t len, i; + char *new_buffer, *dst; + + pos = snapshot->start; + eof = snapshot->eof; + + if (pos == eof) + return; + + len = eof - pos; + + /* + * Initialize records based on a crude estimate of the number + * of references in the file (we'll grow it below if needed): + */ + ALLOC_GROW(records, len / 80 + 20, alloc); + + while (pos < eof) { + eol = memchr(pos, '\n', eof - pos); + if (!eol) + /* The safety check should prevent this. */ + BUG("unterminated line found in packed-refs"); + if (eol - pos < the_hash_algo->hexsz + 2) + die_invalid_line(snapshot->refs->path, + pos, eof - pos); + eol++; + if (eol < eof && *eol == '^') { + /* + * Keep any peeled line together with its + * reference: + */ + const char *peeled_start = eol; + + eol = memchr(peeled_start, '\n', eof - peeled_start); + if (!eol) + /* The safety check should prevent this. */ + BUG("unterminated peeled line found in packed-refs"); + eol++; + } + + ALLOC_GROW(records, nr + 1, alloc); + records[nr].start = pos; + records[nr].len = eol - pos; + nr++; + + if (sorted && + nr > 1 && + cmp_packed_ref_records(&records[nr - 2], + &records[nr - 1]) >= 0) + sorted = 0; + + pos = eol; + } + + if (sorted) + goto cleanup; + + /* We need to sort the memory. First we sort the records array: */ + QSORT(records, nr, cmp_packed_ref_records); + + /* + * Allocate a new chunk of memory, and copy the old memory to + * the new in the order indicated by `records` (not bothering + * with the header line): + */ + new_buffer = xmalloc(len); + for (dst = new_buffer, i = 0; i < nr; i++) { + memcpy(dst, records[i].start, records[i].len); + dst += records[i].len; + } + + /* + * Now munmap the old buffer and use the sorted buffer in its + * place: + */ + clear_snapshot_buffer(snapshot); + snapshot->buf = snapshot->start = new_buffer; + snapshot->eof = new_buffer + len; + +cleanup: + free(records); +} + +/* + * Return a pointer to the start of the record that contains the + * character `*p` (which must be within the buffer). If no other + * record start is found, return `buf`. + */ +static const char *find_start_of_record(const char *buf, const char *p) +{ + while (p > buf && (p[-1] != '\n' || p[0] == '^')) + p--; + return p; +} + +/* + * Return a pointer to the start of the record following the record + * that contains `*p`. If none is found before `end`, return `end`. + */ +static const char *find_end_of_record(const char *p, const char *end) +{ + while (++p < end && (p[-1] != '\n' || p[0] == '^')) + ; + return p; +} + +/* + * We want to be able to compare mmapped reference records quickly, + * without totally parsing them. We can do so because the records are + * LF-terminated, and the refname should start exactly (GIT_SHA1_HEXSZ + * + 1) bytes past the beginning of the record. + * + * But what if the `packed-refs` file contains garbage? We're willing + * to tolerate not detecting the problem, as long as we don't produce + * totally garbled output (we can't afford to check the integrity of + * the whole file during every Git invocation). But we do want to be + * sure that we never read past the end of the buffer in memory and + * perform an illegal memory access. + * + * Guarantee that minimum level of safety by verifying that the last + * record in the file is LF-terminated, and that it has at least + * (GIT_SHA1_HEXSZ + 1) characters before the LF. Die if either of + * these checks fails. + */ +static void verify_buffer_safe(struct snapshot *snapshot) +{ + const char *start = snapshot->start; + const char *eof = snapshot->eof; + const char *last_line; + + if (start == eof) + return; + + last_line = find_start_of_record(start, eof - 1); + if (*(eof - 1) != '\n' || eof - last_line < the_hash_algo->hexsz + 2) + die_invalid_line(snapshot->refs->path, + last_line, eof - last_line); +} + +#define SMALL_FILE_SIZE (32*1024) + +/* + * Depending on `mmap_strategy`, either mmap or read the contents of + * the `packed-refs` file into the snapshot. Return 1 if the file + * existed and was read, or 0 if the file was absent or empty. Die on + * errors. + */ +static int load_contents(struct snapshot *snapshot) +{ + int fd; + struct stat st; + size_t size; + ssize_t bytes_read; + + fd = open(snapshot->refs->path, O_RDONLY); + if (fd < 0) { + if (errno == ENOENT) { + /* + * This is OK; it just means that no + * "packed-refs" file has been written yet, + * which is equivalent to it being empty, + * which is its state when initialized with + * zeros. + */ + return 0; + } else { + die_errno("couldn't read %s", snapshot->refs->path); + } + } + + stat_validity_update(&snapshot->validity, fd); + + if (fstat(fd, &st) < 0) + die_errno("couldn't stat %s", snapshot->refs->path); + size = xsize_t(st.st_size); + + if (!size) { + close(fd); + return 0; + } else if (mmap_strategy == MMAP_NONE || size <= SMALL_FILE_SIZE) { + snapshot->buf = xmalloc(size); + bytes_read = read_in_full(fd, snapshot->buf, size); + if (bytes_read < 0 || bytes_read != size) + die_errno("couldn't read %s", snapshot->refs->path); + snapshot->mmapped = 0; + } else { + snapshot->buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); + snapshot->mmapped = 1; + } + close(fd); + + snapshot->start = snapshot->buf; + snapshot->eof = snapshot->buf + size; + + return 1; +} + +/* + * Find the place in `snapshot->buf` where the start of the record for + * `refname` starts. If `mustexist` is true and the reference doesn't + * exist, then return NULL. If `mustexist` is false and the reference + * doesn't exist, then return the point where that reference would be + * inserted, or `snapshot->eof` (which might be NULL) if it would be + * inserted at the end of the file. In the latter mode, `refname` + * doesn't have to be a proper reference name; for example, one could + * search for "refs/replace/" to find the start of any replace + * references. + * + * The record is sought using a binary search, so `snapshot->buf` must + * be sorted. + */ +static const char *find_reference_location(struct snapshot *snapshot, + const char *refname, int mustexist) +{ + /* + * This is not *quite* a garden-variety binary search, because + * the data we're searching is made up of records, and we + * always need to find the beginning of a record to do a + * comparison. A "record" here is one line for the reference + * itself and zero or one peel lines that start with '^'. Our + * loop invariant is described in the next two comments. + */ + + /* + * A pointer to the character at the start of a record whose + * preceding records all have reference names that come + * *before* `refname`. + */ + const char *lo = snapshot->start; + + /* + * A pointer to a the first character of a record whose + * reference name comes *after* `refname`. + */ + const char *hi = snapshot->eof; + + while (lo != hi) { + const char *mid, *rec; + int cmp; + + mid = lo + (hi - lo) / 2; + rec = find_start_of_record(lo, mid); + cmp = cmp_record_to_refname(rec, refname); + if (cmp < 0) { + lo = find_end_of_record(mid, hi); + } else if (cmp > 0) { + hi = rec; + } else { + return rec; + } + } + + if (mustexist) + return NULL; + else + return lo; +} + +/* + * Create a newly-allocated `snapshot` of the `packed-refs` file in + * its current state and return it. The return value will already have + * its reference count incremented. + * + * A comment line of the form "# pack-refs with: " may contain zero or + * more traits. We interpret the traits as follows: + * + * Neither `peeled` nor `fully-peeled`: + * + * Probably no references are peeled. But if the file contains a + * peeled value for a reference, we will use it. + * + * `peeled`: + * + * References under "refs/tags/", if they *can* be peeled, *are* + * peeled in this file. References outside of "refs/tags/" are + * probably not peeled even if they could have been, but if we find + * a peeled value for such a reference we will use it. + * + * `fully-peeled`: + * + * All references in the file that can be peeled are peeled. + * Inversely (and this is more important), any references in the + * file for which no peeled value is recorded is not peelable. This + * trait should typically be written alongside "peeled" for + * compatibility with older clients, but we do not require it + * (i.e., "peeled" is a no-op if "fully-peeled" is set). + * + * `sorted`: + * + * The references in this file are known to be sorted by refname. + */ +static struct snapshot *create_snapshot(struct packed_ref_store *refs) +{ + struct snapshot *snapshot = xcalloc(1, sizeof(*snapshot)); + int sorted = 0; + + snapshot->refs = refs; + acquire_snapshot(snapshot); + snapshot->peeled = PEELED_NONE; + + if (!load_contents(snapshot)) + return snapshot; + + /* If the file has a header line, process it: */ + if (snapshot->buf < snapshot->eof && *snapshot->buf == '#') { + char *tmp, *p, *eol; + struct string_list traits = STRING_LIST_INIT_NODUP; + + eol = memchr(snapshot->buf, '\n', + snapshot->eof - snapshot->buf); + if (!eol) + die_unterminated_line(refs->path, + snapshot->buf, + snapshot->eof - snapshot->buf); + + tmp = xmemdupz(snapshot->buf, eol - snapshot->buf); + + if (!skip_prefix(tmp, "# pack-refs with:", (const char **)&p)) + die_invalid_line(refs->path, + snapshot->buf, + snapshot->eof - snapshot->buf); + + string_list_split_in_place(&traits, p, ' ', -1); + + if (unsorted_string_list_has_string(&traits, "fully-peeled")) + snapshot->peeled = PEELED_FULLY; + else if (unsorted_string_list_has_string(&traits, "peeled")) + snapshot->peeled = PEELED_TAGS; + + sorted = unsorted_string_list_has_string(&traits, "sorted"); + + /* perhaps other traits later as well */ + + /* The "+ 1" is for the LF character. */ + snapshot->start = eol + 1; + + string_list_clear(&traits, 0); + free(tmp); + } + + verify_buffer_safe(snapshot); + + if (!sorted) { + sort_snapshot(snapshot); + + /* + * Reordering the records might have moved a short one + * to the end of the buffer, so verify the buffer's + * safety again: + */ + verify_buffer_safe(snapshot); + } + + if (mmap_strategy != MMAP_OK && snapshot->mmapped) { + /* + * We don't want to leave the file mmapped, so we are + * forced to make a copy now: + */ + size_t size = snapshot->eof - snapshot->start; + char *buf_copy = xmalloc(size); + + memcpy(buf_copy, snapshot->start, size); + clear_snapshot_buffer(snapshot); + snapshot->buf = snapshot->start = buf_copy; + snapshot->eof = buf_copy + size; + } + + return snapshot; +} + +/* + * Check that `refs->snapshot` (if present) still reflects the + * contents of the `packed-refs` file. If not, clear the snapshot. + */ +static void validate_snapshot(struct packed_ref_store *refs) +{ + if (refs->snapshot && + !stat_validity_check(&refs->snapshot->validity, refs->path)) + clear_snapshot(refs); +} + +/* + * Get the `snapshot` for the specified packed_ref_store, creating and + * populating it if it hasn't been read before or if the file has been + * changed (according to its `validity` field) since it was last read. + * On the other hand, if we hold the lock, then assume that the file + * hasn't been changed out from under us, so skip the extra `stat()` + * call in `stat_validity_check()`. This function does *not* increase + * the snapshot's reference count on behalf of the caller. + */ +static struct snapshot *get_snapshot(struct packed_ref_store *refs) +{ + if (!is_lock_file_locked(&refs->lock)) + validate_snapshot(refs); + + if (!refs->snapshot) + refs->snapshot = create_snapshot(refs); + + return refs->snapshot; +} + +static int packed_read_raw_ref(struct ref_store *ref_store, const char *refname, + struct object_id *oid, struct strbuf *referent UNUSED, + unsigned int *type, int *failure_errno) +{ + struct packed_ref_store *refs = + packed_downcast(ref_store, REF_STORE_READ, "read_raw_ref"); + struct snapshot *snapshot = get_snapshot(refs); + const char *rec; + + *type = 0; + + rec = find_reference_location(snapshot, refname, 1); + + if (!rec) { + /* refname is not a packed reference. */ + *failure_errno = ENOENT; + return -1; + } + + if (get_oid_hex(rec, oid)) + die_invalid_line(refs->path, rec, snapshot->eof - rec); + + *type = REF_ISPACKED; + return 0; +} + +/* + * This value is set in `base.flags` if the peeled value of the + * current reference is known. In that case, `peeled` contains the + * correct peeled value for the reference, which might be `null_oid` + * if the reference is not a tag or if it is broken. + */ +#define REF_KNOWS_PEELED 0x40 + +/* + * An iterator over a snapshot of a `packed-refs` file. + */ +struct packed_ref_iterator { + struct ref_iterator base; + + struct snapshot *snapshot; + + /* The current position in the snapshot's buffer: */ + const char *pos; + + /* The end of the part of the buffer that will be iterated over: */ + const char *eof; + + /* Scratch space for current values: */ + struct object_id oid, peeled; + struct strbuf refname_buf; + + struct repository *repo; + unsigned int flags; +}; + +/* + * Move the iterator to the next record in the snapshot, without + * respect for whether the record is actually required by the current + * iteration. Adjust the fields in `iter` and return `ITER_OK` or + * `ITER_DONE`. This function does not free the iterator in the case + * of `ITER_DONE`. + */ +static int next_record(struct packed_ref_iterator *iter) +{ + const char *p = iter->pos, *eol; + + strbuf_reset(&iter->refname_buf); + + if (iter->pos == iter->eof) + return ITER_DONE; + + iter->base.flags = REF_ISPACKED; + + if (iter->eof - p < the_hash_algo->hexsz + 2 || + parse_oid_hex(p, &iter->oid, &p) || + !isspace(*p++)) + die_invalid_line(iter->snapshot->refs->path, + iter->pos, iter->eof - iter->pos); + + eol = memchr(p, '\n', iter->eof - p); + if (!eol) + die_unterminated_line(iter->snapshot->refs->path, + iter->pos, iter->eof - iter->pos); + + strbuf_add(&iter->refname_buf, p, eol - p); + iter->base.refname = iter->refname_buf.buf; + + if (check_refname_format(iter->base.refname, REFNAME_ALLOW_ONELEVEL)) { + if (!refname_is_safe(iter->base.refname)) + die("packed refname is dangerous: %s", + iter->base.refname); + oidclr(&iter->oid); + iter->base.flags |= REF_BAD_NAME | REF_ISBROKEN; + } + if (iter->snapshot->peeled == PEELED_FULLY || + (iter->snapshot->peeled == PEELED_TAGS && + starts_with(iter->base.refname, "refs/tags/"))) + iter->base.flags |= REF_KNOWS_PEELED; + + iter->pos = eol + 1; + + if (iter->pos < iter->eof && *iter->pos == '^') { + p = iter->pos + 1; + if (iter->eof - p < the_hash_algo->hexsz + 1 || + parse_oid_hex(p, &iter->peeled, &p) || + *p++ != '\n') + die_invalid_line(iter->snapshot->refs->path, + iter->pos, iter->eof - iter->pos); + iter->pos = p; + + /* + * Regardless of what the file header said, we + * definitely know the value of *this* reference. But + * we suppress it if the reference is broken: + */ + if ((iter->base.flags & REF_ISBROKEN)) { + oidclr(&iter->peeled); + iter->base.flags &= ~REF_KNOWS_PEELED; + } else { + iter->base.flags |= REF_KNOWS_PEELED; + } + } else { + oidclr(&iter->peeled); + } + + return ITER_OK; +} + +static int packed_ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + struct packed_ref_iterator *iter = + (struct packed_ref_iterator *)ref_iterator; + int ok; + + while ((ok = next_record(iter)) == ITER_OK) { + if (iter->flags & DO_FOR_EACH_PER_WORKTREE_ONLY && + !is_per_worktree_ref(iter->base.refname)) + continue; + + if (!(iter->flags & DO_FOR_EACH_INCLUDE_BROKEN) && + !ref_resolves_to_object(iter->base.refname, iter->repo, + &iter->oid, iter->flags)) + continue; + + return ITER_OK; + } + + if (ref_iterator_abort(ref_iterator) != ITER_DONE) + ok = ITER_ERROR; + + return ok; +} + +static int packed_ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) +{ + struct packed_ref_iterator *iter = + (struct packed_ref_iterator *)ref_iterator; + + if (iter->repo != the_repository) + BUG("peeling for non-the_repository is not supported"); + + if ((iter->base.flags & REF_KNOWS_PEELED)) { + oidcpy(peeled, &iter->peeled); + return is_null_oid(&iter->peeled) ? -1 : 0; + } else if ((iter->base.flags & (REF_ISBROKEN | REF_ISSYMREF))) { + return -1; + } else { + return peel_object(&iter->oid, peeled) ? -1 : 0; + } +} + +static int packed_ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + struct packed_ref_iterator *iter = + (struct packed_ref_iterator *)ref_iterator; + int ok = ITER_DONE; + + strbuf_release(&iter->refname_buf); + release_snapshot(iter->snapshot); + base_ref_iterator_free(ref_iterator); + return ok; +} + +static struct ref_iterator_vtable packed_ref_iterator_vtable = { + .advance = packed_ref_iterator_advance, + .peel = packed_ref_iterator_peel, + .abort = packed_ref_iterator_abort +}; + +static struct ref_iterator *packed_ref_iterator_begin( + struct ref_store *ref_store, + const char *prefix, unsigned int flags) +{ + struct packed_ref_store *refs; + struct snapshot *snapshot; + const char *start; + struct packed_ref_iterator *iter; + struct ref_iterator *ref_iterator; + unsigned int required_flags = REF_STORE_READ; + + if (!(flags & DO_FOR_EACH_INCLUDE_BROKEN)) + required_flags |= REF_STORE_ODB; + refs = packed_downcast(ref_store, required_flags, "ref_iterator_begin"); + + /* + * Note that `get_snapshot()` internally checks whether the + * snapshot is up to date with what is on disk, and re-reads + * it if not. + */ + snapshot = get_snapshot(refs); + + if (prefix && *prefix) + start = find_reference_location(snapshot, prefix, 0); + else + start = snapshot->start; + + if (start == snapshot->eof) + return empty_ref_iterator_begin(); + + CALLOC_ARRAY(iter, 1); + ref_iterator = &iter->base; + base_ref_iterator_init(ref_iterator, &packed_ref_iterator_vtable, 1); + + iter->snapshot = snapshot; + acquire_snapshot(snapshot); + + iter->pos = start; + iter->eof = snapshot->eof; + strbuf_init(&iter->refname_buf, 0); + + iter->base.oid = &iter->oid; + + iter->repo = ref_store->repo; + iter->flags = flags; + + if (prefix && *prefix) + /* Stop iteration after we've gone *past* prefix: */ + ref_iterator = prefix_ref_iterator_begin(ref_iterator, prefix, 0); + + return ref_iterator; +} + +/* + * Write an entry to the packed-refs file for the specified refname. + * If peeled is non-NULL, write it as the entry's peeled value. On + * error, return a nonzero value and leave errno set at the value left + * by the failing call to `fprintf()`. + */ +static int write_packed_entry(FILE *fh, const char *refname, + const struct object_id *oid, + const struct object_id *peeled) +{ + if (fprintf(fh, "%s %s\n", oid_to_hex(oid), refname) < 0 || + (peeled && fprintf(fh, "^%s\n", oid_to_hex(peeled)) < 0)) + return -1; + + return 0; +} + +int packed_refs_lock(struct ref_store *ref_store, int flags, struct strbuf *err) +{ + struct packed_ref_store *refs = + packed_downcast(ref_store, REF_STORE_WRITE | REF_STORE_MAIN, + "packed_refs_lock"); + static int timeout_configured = 0; + static int timeout_value = 1000; + + if (!timeout_configured) { + git_config_get_int("core.packedrefstimeout", &timeout_value); + timeout_configured = 1; + } + + /* + * Note that we close the lockfile immediately because we + * don't write new content to it, but rather to a separate + * tempfile. + */ + if (hold_lock_file_for_update_timeout( + &refs->lock, + refs->path, + flags, timeout_value) < 0) { + unable_to_lock_message(refs->path, errno, err); + return -1; + } + + if (close_lock_file_gently(&refs->lock)) { + strbuf_addf(err, "unable to close %s: %s", refs->path, strerror(errno)); + rollback_lock_file(&refs->lock); + return -1; + } + + /* + * There is a stat-validity problem might cause `update-ref -d` + * lost the newly commit of a ref, because a new `packed-refs` + * file might has the same on-disk file attributes such as + * timestamp, file size and inode value, but has a changed + * ref value. + * + * This could happen with a very small chance when + * `update-ref -d` is called and at the same time another + * `pack-refs --all` process is running. + * + * Now that we hold the `packed-refs` lock, it is important + * to make sure we could read the latest version of + * `packed-refs` file no matter we have just mmap it or not. + * So what need to do is clear the snapshot if we hold it + * already. + */ + clear_snapshot(refs); + + /* + * Now make sure that the packed-refs file as it exists in the + * locked state is loaded into the snapshot: + */ + get_snapshot(refs); + return 0; +} + +void packed_refs_unlock(struct ref_store *ref_store) +{ + struct packed_ref_store *refs = packed_downcast( + ref_store, + REF_STORE_READ | REF_STORE_WRITE, + "packed_refs_unlock"); + + if (!is_lock_file_locked(&refs->lock)) + BUG("packed_refs_unlock() called when not locked"); + rollback_lock_file(&refs->lock); +} + +int packed_refs_is_locked(struct ref_store *ref_store) +{ + struct packed_ref_store *refs = packed_downcast( + ref_store, + REF_STORE_READ | REF_STORE_WRITE, + "packed_refs_is_locked"); + + return is_lock_file_locked(&refs->lock); +} + +/* + * The packed-refs header line that we write out. Perhaps other traits + * will be added later. + * + * Note that earlier versions of Git used to parse these traits by + * looking for " trait " in the line. For this reason, the space after + * the colon and the trailing space are required. + */ +static const char PACKED_REFS_HEADER[] = + "# pack-refs with: peeled fully-peeled sorted \n"; + +static int packed_init_db(struct ref_store *ref_store UNUSED, + struct strbuf *err UNUSED) +{ + /* Nothing to do. */ + return 0; +} + +/* + * Write the packed refs from the current snapshot to the packed-refs + * tempfile, incorporating any changes from `updates`. `updates` must + * be a sorted string list whose keys are the refnames and whose util + * values are `struct ref_update *`. On error, rollback the tempfile, + * write an error message to `err`, and return a nonzero value. + * + * The packfile must be locked before calling this function and will + * remain locked when it is done. + */ +static int write_with_updates(struct packed_ref_store *refs, + struct string_list *updates, + struct strbuf *err) +{ + struct ref_iterator *iter = NULL; + size_t i; + int ok; + FILE *out; + struct strbuf sb = STRBUF_INIT; + char *packed_refs_path; + + if (!is_lock_file_locked(&refs->lock)) + BUG("write_with_updates() called while unlocked"); + + /* + * If packed-refs is a symlink, we want to overwrite the + * symlinked-to file, not the symlink itself. Also, put the + * staging file next to it: + */ + packed_refs_path = get_locked_file_path(&refs->lock); + strbuf_addf(&sb, "%s.new", packed_refs_path); + free(packed_refs_path); + refs->tempfile = create_tempfile(sb.buf); + if (!refs->tempfile) { + strbuf_addf(err, "unable to create file %s: %s", + sb.buf, strerror(errno)); + strbuf_release(&sb); + return -1; + } + strbuf_release(&sb); + + out = fdopen_tempfile(refs->tempfile, "w"); + if (!out) { + strbuf_addf(err, "unable to fdopen packed-refs tempfile: %s", + strerror(errno)); + goto error; + } + + if (fprintf(out, "%s", PACKED_REFS_HEADER) < 0) + goto write_error; + + /* + * We iterate in parallel through the current list of refs and + * the list of updates, processing an entry from at least one + * of the lists each time through the loop. When the current + * list of refs is exhausted, set iter to NULL. When the list + * of updates is exhausted, leave i set to updates->nr. + */ + iter = packed_ref_iterator_begin(&refs->base, "", + DO_FOR_EACH_INCLUDE_BROKEN); + if ((ok = ref_iterator_advance(iter)) != ITER_OK) + iter = NULL; + + i = 0; + + while (iter || i < updates->nr) { + struct ref_update *update = NULL; + int cmp; + + if (i >= updates->nr) { + cmp = -1; + } else { + update = updates->items[i].util; + + if (!iter) + cmp = +1; + else + cmp = strcmp(iter->refname, update->refname); + } + + if (!cmp) { + /* + * There is both an old value and an update + * for this reference. Check the old value if + * necessary: + */ + if ((update->flags & REF_HAVE_OLD)) { + if (is_null_oid(&update->old_oid)) { + strbuf_addf(err, "cannot update ref '%s': " + "reference already exists", + update->refname); + goto error; + } else if (!oideq(&update->old_oid, iter->oid)) { + strbuf_addf(err, "cannot update ref '%s': " + "is at %s but expected %s", + update->refname, + oid_to_hex(iter->oid), + oid_to_hex(&update->old_oid)); + goto error; + } + } + + /* Now figure out what to use for the new value: */ + if ((update->flags & REF_HAVE_NEW)) { + /* + * The update takes precedence. Skip + * the iterator over the unneeded + * value. + */ + if ((ok = ref_iterator_advance(iter)) != ITER_OK) + iter = NULL; + cmp = +1; + } else { + /* + * The update doesn't actually want to + * change anything. We're done with it. + */ + i++; + cmp = -1; + } + } else if (cmp > 0) { + /* + * There is no old value but there is an + * update for this reference. Make sure that + * the update didn't expect an existing value: + */ + if ((update->flags & REF_HAVE_OLD) && + !is_null_oid(&update->old_oid)) { + strbuf_addf(err, "cannot update ref '%s': " + "reference is missing but expected %s", + update->refname, + oid_to_hex(&update->old_oid)); + goto error; + } + } + + if (cmp < 0) { + /* Pass the old reference through. */ + + struct object_id peeled; + int peel_error = ref_iterator_peel(iter, &peeled); + + if (write_packed_entry(out, iter->refname, + iter->oid, + peel_error ? NULL : &peeled)) + goto write_error; + + if ((ok = ref_iterator_advance(iter)) != ITER_OK) + iter = NULL; + } else if (is_null_oid(&update->new_oid)) { + /* + * The update wants to delete the reference, + * and the reference either didn't exist or we + * have already skipped it. So we're done with + * the update (and don't have to write + * anything). + */ + i++; + } else { + struct object_id peeled; + int peel_error = peel_object(&update->new_oid, + &peeled); + + if (write_packed_entry(out, update->refname, + &update->new_oid, + peel_error ? NULL : &peeled)) + goto write_error; + + i++; + } + } + + if (ok != ITER_DONE) { + strbuf_addstr(err, "unable to write packed-refs file: " + "error iterating over old contents"); + goto error; + } + + if (fsync_component(FSYNC_COMPONENT_REFERENCE, get_tempfile_fd(refs->tempfile)) || + close_tempfile_gently(refs->tempfile)) { + strbuf_addf(err, "error closing file %s: %s", + get_tempfile_path(refs->tempfile), + strerror(errno)); + strbuf_release(&sb); + delete_tempfile(&refs->tempfile); + return -1; + } + + return 0; + +write_error: + strbuf_addf(err, "error writing to %s: %s", + get_tempfile_path(refs->tempfile), strerror(errno)); + +error: + if (iter) + ref_iterator_abort(iter); + + delete_tempfile(&refs->tempfile); + return -1; +} + +int is_packed_transaction_needed(struct ref_store *ref_store, + struct ref_transaction *transaction) +{ + struct packed_ref_store *refs = packed_downcast( + ref_store, + REF_STORE_READ, + "is_packed_transaction_needed"); + struct strbuf referent = STRBUF_INIT; + size_t i; + int ret; + + if (!is_lock_file_locked(&refs->lock)) + BUG("is_packed_transaction_needed() called while unlocked"); + + /* + * We're only going to bother returning false for the common, + * trivial case that references are only being deleted, their + * old values are not being checked, and the old `packed-refs` + * file doesn't contain any of those reference(s). This gives + * false positives for some other cases that could + * theoretically be optimized away: + * + * 1. It could be that the old value is being verified without + * setting a new value. In this case, we could verify the + * old value here and skip the update if it agrees. If it + * disagrees, we could either let the update go through + * (the actual commit would re-detect and report the + * problem), or come up with a way of reporting such an + * error to *our* caller. + * + * 2. It could be that a new value is being set, but that it + * is identical to the current packed value of the + * reference. + * + * Neither of these cases will come up in the current code, + * because the only caller of this function passes to it a + * transaction that only includes `delete` updates with no + * `old_id`. Even if that ever changes, false positives only + * cause an optimization to be missed; they do not affect + * correctness. + */ + + /* + * Start with the cheap checks that don't require old + * reference values to be read: + */ + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; + + if (update->flags & REF_HAVE_OLD) + /* Have to check the old value -> needed. */ + return 1; + + if ((update->flags & REF_HAVE_NEW) && !is_null_oid(&update->new_oid)) + /* Have to set a new value -> needed. */ + return 1; + } + + /* + * The transaction isn't checking any old values nor is it + * setting any nonzero new values, so it still might be able + * to be skipped. Now do the more expensive check: the update + * is needed if any of the updates is a delete, and the old + * `packed-refs` file contains a value for that reference. + */ + ret = 0; + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; + int failure_errno; + unsigned int type; + struct object_id oid; + + if (!(update->flags & REF_HAVE_NEW)) + /* + * This reference isn't being deleted -> not + * needed. + */ + continue; + + if (!refs_read_raw_ref(ref_store, update->refname, &oid, + &referent, &type, &failure_errno) || + failure_errno != ENOENT) { + /* + * We have to actually delete that reference + * -> this transaction is needed. + */ + ret = 1; + break; + } + } + + strbuf_release(&referent); + return ret; +} + +struct packed_transaction_backend_data { + /* True iff the transaction owns the packed-refs lock. */ + int own_lock; + + struct string_list updates; +}; + +static void packed_transaction_cleanup(struct packed_ref_store *refs, + struct ref_transaction *transaction) +{ + struct packed_transaction_backend_data *data = transaction->backend_data; + + if (data) { + string_list_clear(&data->updates, 0); + + if (is_tempfile_active(refs->tempfile)) + delete_tempfile(&refs->tempfile); + + if (data->own_lock && is_lock_file_locked(&refs->lock)) { + packed_refs_unlock(&refs->base); + data->own_lock = 0; + } + + free(data); + transaction->backend_data = NULL; + } + + transaction->state = REF_TRANSACTION_CLOSED; +} + +static int packed_transaction_prepare(struct ref_store *ref_store, + struct ref_transaction *transaction, + struct strbuf *err) +{ + struct packed_ref_store *refs = packed_downcast( + ref_store, + REF_STORE_READ | REF_STORE_WRITE | REF_STORE_ODB, + "ref_transaction_prepare"); + struct packed_transaction_backend_data *data; + size_t i; + int ret = TRANSACTION_GENERIC_ERROR; + + /* + * Note that we *don't* skip transactions with zero updates, + * because such a transaction might be executed for the side + * effect of ensuring that all of the references are peeled or + * ensuring that the `packed-refs` file is sorted. If the + * caller wants to optimize away empty transactions, it should + * do so itself. + */ + + CALLOC_ARRAY(data, 1); + string_list_init_nodup(&data->updates); + + transaction->backend_data = data; + + /* + * Stick the updates in a string list by refname so that we + * can sort them: + */ + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; + struct string_list_item *item = + string_list_append(&data->updates, update->refname); + + /* Store a pointer to update in item->util: */ + item->util = update; + } + string_list_sort(&data->updates); + + if (ref_update_reject_duplicates(&data->updates, err)) + goto failure; + + if (!is_lock_file_locked(&refs->lock)) { + if (packed_refs_lock(ref_store, 0, err)) + goto failure; + data->own_lock = 1; + } + + if (write_with_updates(refs, &data->updates, err)) + goto failure; + + transaction->state = REF_TRANSACTION_PREPARED; + return 0; + +failure: + packed_transaction_cleanup(refs, transaction); + return ret; +} + +static int packed_transaction_abort(struct ref_store *ref_store, + struct ref_transaction *transaction, + struct strbuf *err UNUSED) +{ + struct packed_ref_store *refs = packed_downcast( + ref_store, + REF_STORE_READ | REF_STORE_WRITE | REF_STORE_ODB, + "ref_transaction_abort"); + + packed_transaction_cleanup(refs, transaction); + return 0; +} + +static int packed_transaction_finish(struct ref_store *ref_store, + struct ref_transaction *transaction, + struct strbuf *err) +{ + struct packed_ref_store *refs = packed_downcast( + ref_store, + REF_STORE_READ | REF_STORE_WRITE | REF_STORE_ODB, + "ref_transaction_finish"); + int ret = TRANSACTION_GENERIC_ERROR; + char *packed_refs_path; + + clear_snapshot(refs); + + packed_refs_path = get_locked_file_path(&refs->lock); + if (rename_tempfile(&refs->tempfile, packed_refs_path)) { + strbuf_addf(err, "error replacing %s: %s", + refs->path, strerror(errno)); + goto cleanup; + } + + ret = 0; + +cleanup: + free(packed_refs_path); + packed_transaction_cleanup(refs, transaction); + return ret; +} + +static int packed_initial_transaction_commit(struct ref_store *ref_store UNUSED, + struct ref_transaction *transaction, + struct strbuf *err) +{ + return ref_transaction_commit(transaction, err); +} + +static int packed_delete_refs(struct ref_store *ref_store, const char *msg, + struct string_list *refnames, unsigned int flags) +{ + struct packed_ref_store *refs = + packed_downcast(ref_store, REF_STORE_WRITE, "delete_refs"); + struct strbuf err = STRBUF_INIT; + struct ref_transaction *transaction; + struct string_list_item *item; + int ret; + + (void)refs; /* We need the check above, but don't use the variable */ + + if (!refnames->nr) + return 0; + + /* + * Since we don't check the references' old_oids, the + * individual updates can't fail, so we can pack all of the + * updates into a single transaction. + */ + + transaction = ref_store_transaction_begin(ref_store, &err); + if (!transaction) + return -1; + + for_each_string_list_item(item, refnames) { + if (ref_transaction_delete(transaction, item->string, NULL, + flags, msg, &err)) { + warning(_("could not delete reference %s: %s"), + item->string, err.buf); + strbuf_reset(&err); + } + } + + ret = ref_transaction_commit(transaction, &err); + + if (ret) { + if (refnames->nr == 1) + error(_("could not delete reference %s: %s"), + refnames->items[0].string, err.buf); + else + error(_("could not delete references: %s"), err.buf); + } + + ref_transaction_free(transaction); + strbuf_release(&err); + return ret; +} + +static int packed_pack_refs(struct ref_store *ref_store UNUSED, + unsigned int flags UNUSED) +{ + /* + * Packed refs are already packed. It might be that loose refs + * are packed *into* a packed refs store, but that is done by + * updating the packed references via a transaction. + */ + return 0; +} + +static struct ref_iterator *packed_reflog_iterator_begin(struct ref_store *ref_store UNUSED) +{ + return empty_ref_iterator_begin(); +} + +struct ref_storage_be refs_be_packed = { + .next = NULL, + .name = "packed", + .init = packed_ref_store_create, + .init_db = packed_init_db, + .transaction_prepare = packed_transaction_prepare, + .transaction_finish = packed_transaction_finish, + .transaction_abort = packed_transaction_abort, + .initial_transaction_commit = packed_initial_transaction_commit, + + .pack_refs = packed_pack_refs, + .create_symref = NULL, + .delete_refs = packed_delete_refs, + .rename_ref = NULL, + .copy_ref = NULL, + + .iterator_begin = packed_ref_iterator_begin, + .read_raw_ref = packed_read_raw_ref, + .read_symbolic_ref = NULL, + + .reflog_iterator_begin = packed_reflog_iterator_begin, + .for_each_reflog_ent = NULL, + .for_each_reflog_ent_reverse = NULL, + .reflog_exists = NULL, + .create_reflog = NULL, + .delete_reflog = NULL, + .reflog_expire = NULL, +}; diff --git a/refs/packed-backend.h b/refs/packed-backend.h new file mode 100644 index 0000000..9dd8a34 --- /dev/null +++ b/refs/packed-backend.h @@ -0,0 +1,39 @@ +#ifndef REFS_PACKED_BACKEND_H +#define REFS_PACKED_BACKEND_H + +struct repository; +struct ref_transaction; + +/* + * Support for storing references in a `packed-refs` file. + * + * Note that this backend doesn't check for D/F conflicts, because it + * doesn't care about them. But usually it should be wrapped in a + * `files_ref_store` that prevents D/F conflicts from being created, + * even among packed refs. + */ + +struct ref_store *packed_ref_store_create(struct repository *repo, + const char *gitdir, + unsigned int store_flags); + +/* + * Lock the packed-refs file for writing. Flags is passed to + * hold_lock_file_for_update(). Return 0 on success. On errors, write + * an error message to `err` and return a nonzero value. + */ +int packed_refs_lock(struct ref_store *ref_store, int flags, struct strbuf *err); + +void packed_refs_unlock(struct ref_store *ref_store); +int packed_refs_is_locked(struct ref_store *ref_store); + +/* + * Return true if `transaction` really needs to be carried out against + * the specified packed_ref_store, or false if it can be skipped + * (i.e., because it is an obvious NOOP). `ref_store` must be locked + * before calling this function. + */ +int is_packed_transaction_needed(struct ref_store *ref_store, + struct ref_transaction *transaction); + +#endif /* REFS_PACKED_BACKEND_H */ diff --git a/refs/ref-cache.c b/refs/ref-cache.c new file mode 100644 index 0000000..32afd8a --- /dev/null +++ b/refs/ref-cache.c @@ -0,0 +1,504 @@ +#include "../cache.h" +#include "../refs.h" +#include "refs-internal.h" +#include "ref-cache.h" +#include "../iterator.h" + +void add_entry_to_dir(struct ref_dir *dir, struct ref_entry *entry) +{ + ALLOC_GROW(dir->entries, dir->nr + 1, dir->alloc); + dir->entries[dir->nr++] = entry; + /* optimize for the case that entries are added in order */ + if (dir->nr == 1 || + (dir->nr == dir->sorted + 1 && + strcmp(dir->entries[dir->nr - 2]->name, + dir->entries[dir->nr - 1]->name) < 0)) + dir->sorted = dir->nr; +} + +struct ref_dir *get_ref_dir(struct ref_entry *entry) +{ + struct ref_dir *dir; + assert(entry->flag & REF_DIR); + dir = &entry->u.subdir; + if (entry->flag & REF_INCOMPLETE) { + if (!dir->cache->fill_ref_dir) + BUG("incomplete ref_store without fill_ref_dir function"); + + dir->cache->fill_ref_dir(dir->cache->ref_store, dir, entry->name); + entry->flag &= ~REF_INCOMPLETE; + } + return dir; +} + +struct ref_entry *create_ref_entry(const char *refname, + const struct object_id *oid, int flag) +{ + struct ref_entry *ref; + + FLEX_ALLOC_STR(ref, name, refname); + oidcpy(&ref->u.value.oid, oid); + ref->flag = flag; + return ref; +} + +struct ref_cache *create_ref_cache(struct ref_store *refs, + fill_ref_dir_fn *fill_ref_dir) +{ + struct ref_cache *ret = xcalloc(1, sizeof(*ret)); + + ret->ref_store = refs; + ret->fill_ref_dir = fill_ref_dir; + ret->root = create_dir_entry(ret, "", 0); + return ret; +} + +static void clear_ref_dir(struct ref_dir *dir); + +static void free_ref_entry(struct ref_entry *entry) +{ + if (entry->flag & REF_DIR) { + /* + * Do not use get_ref_dir() here, as that might + * trigger the reading of loose refs. + */ + clear_ref_dir(&entry->u.subdir); + } + free(entry); +} + +void free_ref_cache(struct ref_cache *cache) +{ + free_ref_entry(cache->root); + free(cache); +} + +/* + * Clear and free all entries in dir, recursively. + */ +static void clear_ref_dir(struct ref_dir *dir) +{ + int i; + for (i = 0; i < dir->nr; i++) + free_ref_entry(dir->entries[i]); + FREE_AND_NULL(dir->entries); + dir->sorted = dir->nr = dir->alloc = 0; +} + +struct ref_entry *create_dir_entry(struct ref_cache *cache, + const char *dirname, size_t len) +{ + struct ref_entry *direntry; + + FLEX_ALLOC_MEM(direntry, name, dirname, len); + direntry->u.subdir.cache = cache; + direntry->flag = REF_DIR | REF_INCOMPLETE; + return direntry; +} + +static int ref_entry_cmp(const void *a, const void *b) +{ + struct ref_entry *one = *(struct ref_entry **)a; + struct ref_entry *two = *(struct ref_entry **)b; + return strcmp(one->name, two->name); +} + +static void sort_ref_dir(struct ref_dir *dir); + +struct string_slice { + size_t len; + const char *str; +}; + +static int ref_entry_cmp_sslice(const void *key_, const void *ent_) +{ + const struct string_slice *key = key_; + const struct ref_entry *ent = *(const struct ref_entry * const *)ent_; + int cmp = strncmp(key->str, ent->name, key->len); + if (cmp) + return cmp; + return '\0' - (unsigned char)ent->name[key->len]; +} + +int search_ref_dir(struct ref_dir *dir, const char *refname, size_t len) +{ + struct ref_entry **r; + struct string_slice key; + + if (refname == NULL || !dir->nr) + return -1; + + sort_ref_dir(dir); + key.len = len; + key.str = refname; + r = bsearch(&key, dir->entries, dir->nr, sizeof(*dir->entries), + ref_entry_cmp_sslice); + + if (!r) + return -1; + + return r - dir->entries; +} + +/* + * Search for a directory entry directly within dir (without + * recursing). Sort dir if necessary. subdirname must be a directory + * name (i.e., end in '/'). Returns NULL if the desired + * directory cannot be found. dir must already be complete. + */ +static struct ref_dir *search_for_subdir(struct ref_dir *dir, + const char *subdirname, size_t len) +{ + int entry_index = search_ref_dir(dir, subdirname, len); + struct ref_entry *entry; + + if (entry_index == -1) + return NULL; + + entry = dir->entries[entry_index]; + return get_ref_dir(entry); +} + +/* + * If refname is a reference name, find the ref_dir within the dir + * tree that should hold refname. If refname is a directory name + * (i.e., it ends in '/'), then return that ref_dir itself. dir must + * represent the top-level directory and must already be complete. + * Sort ref_dirs and recurse into subdirectories as necessary. Will + * return NULL if the desired directory cannot be found. + */ +static struct ref_dir *find_containing_dir(struct ref_dir *dir, + const char *refname) +{ + const char *slash; + for (slash = strchr(refname, '/'); slash; slash = strchr(slash + 1, '/')) { + size_t dirnamelen = slash - refname + 1; + struct ref_dir *subdir; + subdir = search_for_subdir(dir, refname, dirnamelen); + if (!subdir) { + dir = NULL; + break; + } + dir = subdir; + } + + return dir; +} + +struct ref_entry *find_ref_entry(struct ref_dir *dir, const char *refname) +{ + int entry_index; + struct ref_entry *entry; + dir = find_containing_dir(dir, refname); + if (!dir) + return NULL; + entry_index = search_ref_dir(dir, refname, strlen(refname)); + if (entry_index == -1) + return NULL; + entry = dir->entries[entry_index]; + return (entry->flag & REF_DIR) ? NULL : entry; +} + +/* + * Emit a warning and return true iff ref1 and ref2 have the same name + * and the same oid. Die if they have the same name but different + * oids. + */ +static int is_dup_ref(const struct ref_entry *ref1, const struct ref_entry *ref2) +{ + if (strcmp(ref1->name, ref2->name)) + return 0; + + /* Duplicate name; make sure that they don't conflict: */ + + if ((ref1->flag & REF_DIR) || (ref2->flag & REF_DIR)) + /* This is impossible by construction */ + die("Reference directory conflict: %s", ref1->name); + + if (!oideq(&ref1->u.value.oid, &ref2->u.value.oid)) + die("Duplicated ref, and SHA1s don't match: %s", ref1->name); + + warning("Duplicated ref: %s", ref1->name); + return 1; +} + +/* + * Sort the entries in dir non-recursively (if they are not already + * sorted) and remove any duplicate entries. + */ +static void sort_ref_dir(struct ref_dir *dir) +{ + int i, j; + struct ref_entry *last = NULL; + + /* + * This check also prevents passing a zero-length array to qsort(), + * which is a problem on some platforms. + */ + if (dir->sorted == dir->nr) + return; + + QSORT(dir->entries, dir->nr, ref_entry_cmp); + + /* Remove any duplicates: */ + for (i = 0, j = 0; j < dir->nr; j++) { + struct ref_entry *entry = dir->entries[j]; + if (last && is_dup_ref(last, entry)) + free_ref_entry(entry); + else + last = dir->entries[i++] = entry; + } + dir->sorted = dir->nr = i; +} + +enum prefix_state { + /* All refs within the directory would match prefix: */ + PREFIX_CONTAINS_DIR, + + /* Some, but not all, refs within the directory might match prefix: */ + PREFIX_WITHIN_DIR, + + /* No refs within the directory could possibly match prefix: */ + PREFIX_EXCLUDES_DIR +}; + +/* + * Return a `prefix_state` constant describing the relationship + * between the directory with the specified `dirname` and `prefix`. + */ +static enum prefix_state overlaps_prefix(const char *dirname, + const char *prefix) +{ + while (*prefix && *dirname == *prefix) { + dirname++; + prefix++; + } + if (!*prefix) + return PREFIX_CONTAINS_DIR; + else if (!*dirname) + return PREFIX_WITHIN_DIR; + else + return PREFIX_EXCLUDES_DIR; +} + +/* + * Load all of the refs from `dir` (recursively) that could possibly + * contain references matching `prefix` into our in-memory cache. If + * `prefix` is NULL, prime unconditionally. + */ +static void prime_ref_dir(struct ref_dir *dir, const char *prefix) +{ + /* + * The hard work of loading loose refs is done by get_ref_dir(), so we + * just need to recurse through all of the sub-directories. We do not + * even need to care about sorting, as traversal order does not matter + * to us. + */ + int i; + for (i = 0; i < dir->nr; i++) { + struct ref_entry *entry = dir->entries[i]; + if (!(entry->flag & REF_DIR)) { + /* Not a directory; no need to recurse. */ + } else if (!prefix) { + /* Recurse in any case: */ + prime_ref_dir(get_ref_dir(entry), NULL); + } else { + switch (overlaps_prefix(entry->name, prefix)) { + case PREFIX_CONTAINS_DIR: + /* + * Recurse, and from here down we + * don't have to check the prefix + * anymore: + */ + prime_ref_dir(get_ref_dir(entry), NULL); + break; + case PREFIX_WITHIN_DIR: + prime_ref_dir(get_ref_dir(entry), prefix); + break; + case PREFIX_EXCLUDES_DIR: + /* No need to prime this directory. */ + break; + } + } + } +} + +/* + * A level in the reference hierarchy that is currently being iterated + * through. + */ +struct cache_ref_iterator_level { + /* + * The ref_dir being iterated over at this level. The ref_dir + * is sorted before being stored here. + */ + struct ref_dir *dir; + + enum prefix_state prefix_state; + + /* + * The index of the current entry within dir (which might + * itself be a directory). If index == -1, then the iteration + * hasn't yet begun. If index == dir->nr, then the iteration + * through this level is over. + */ + int index; +}; + +/* + * Represent an iteration through a ref_dir in the memory cache. The + * iteration recurses through subdirectories. + */ +struct cache_ref_iterator { + struct ref_iterator base; + + /* + * The number of levels currently on the stack. This is always + * at least 1, because when it becomes zero the iteration is + * ended and this struct is freed. + */ + size_t levels_nr; + + /* The number of levels that have been allocated on the stack */ + size_t levels_alloc; + + /* + * Only include references with this prefix in the iteration. + * The prefix is matched textually, without regard for path + * component boundaries. + */ + const char *prefix; + + /* + * A stack of levels. levels[0] is the uppermost level that is + * being iterated over in this iteration. (This is not + * necessary the top level in the references hierarchy. If we + * are iterating through a subtree, then levels[0] will hold + * the ref_dir for that subtree, and subsequent levels will go + * on from there.) + */ + struct cache_ref_iterator_level *levels; + + struct repository *repo; +}; + +static int cache_ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + struct cache_ref_iterator *iter = + (struct cache_ref_iterator *)ref_iterator; + + while (1) { + struct cache_ref_iterator_level *level = + &iter->levels[iter->levels_nr - 1]; + struct ref_dir *dir = level->dir; + struct ref_entry *entry; + enum prefix_state entry_prefix_state; + + if (level->index == -1) + sort_ref_dir(dir); + + if (++level->index == level->dir->nr) { + /* This level is exhausted; pop up a level */ + if (--iter->levels_nr == 0) + return ref_iterator_abort(ref_iterator); + + continue; + } + + entry = dir->entries[level->index]; + + if (level->prefix_state == PREFIX_WITHIN_DIR) { + entry_prefix_state = overlaps_prefix(entry->name, iter->prefix); + if (entry_prefix_state == PREFIX_EXCLUDES_DIR) + continue; + } else { + entry_prefix_state = level->prefix_state; + } + + if (entry->flag & REF_DIR) { + /* push down a level */ + ALLOC_GROW(iter->levels, iter->levels_nr + 1, + iter->levels_alloc); + + level = &iter->levels[iter->levels_nr++]; + level->dir = get_ref_dir(entry); + level->prefix_state = entry_prefix_state; + level->index = -1; + } else { + iter->base.refname = entry->name; + iter->base.oid = &entry->u.value.oid; + iter->base.flags = entry->flag; + return ITER_OK; + } + } +} + +static int cache_ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) +{ + struct cache_ref_iterator *iter = + (struct cache_ref_iterator *)ref_iterator; + + if (iter->repo != the_repository) + BUG("peeling for non-the_repository is not supported"); + return peel_object(ref_iterator->oid, peeled) ? -1 : 0; +} + +static int cache_ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + struct cache_ref_iterator *iter = + (struct cache_ref_iterator *)ref_iterator; + + free((char *)iter->prefix); + free(iter->levels); + base_ref_iterator_free(ref_iterator); + return ITER_DONE; +} + +static struct ref_iterator_vtable cache_ref_iterator_vtable = { + .advance = cache_ref_iterator_advance, + .peel = cache_ref_iterator_peel, + .abort = cache_ref_iterator_abort +}; + +struct ref_iterator *cache_ref_iterator_begin(struct ref_cache *cache, + const char *prefix, + struct repository *repo, + int prime_dir) +{ + struct ref_dir *dir; + struct cache_ref_iterator *iter; + struct ref_iterator *ref_iterator; + struct cache_ref_iterator_level *level; + + dir = get_ref_dir(cache->root); + if (prefix && *prefix) + dir = find_containing_dir(dir, prefix); + if (!dir) + /* There's nothing to iterate over. */ + return empty_ref_iterator_begin(); + + if (prime_dir) + prime_ref_dir(dir, prefix); + + CALLOC_ARRAY(iter, 1); + ref_iterator = &iter->base; + base_ref_iterator_init(ref_iterator, &cache_ref_iterator_vtable, 1); + ALLOC_GROW(iter->levels, 10, iter->levels_alloc); + + iter->levels_nr = 1; + level = &iter->levels[0]; + level->index = -1; + level->dir = dir; + + if (prefix && *prefix) { + iter->prefix = xstrdup(prefix); + level->prefix_state = PREFIX_WITHIN_DIR; + } else { + level->prefix_state = PREFIX_CONTAINS_DIR; + } + + iter->repo = repo; + + return ref_iterator; +} diff --git a/refs/ref-cache.h b/refs/ref-cache.h new file mode 100644 index 0000000..850d9d3 --- /dev/null +++ b/refs/ref-cache.h @@ -0,0 +1,220 @@ +#ifndef REFS_REF_CACHE_H +#define REFS_REF_CACHE_H + +#include "cache.h" + +struct ref_dir; +struct ref_store; + +/* + * If this ref_cache is filled lazily, this function is used to load + * information into the specified ref_dir (shallow or deep, at the + * option of the ref_store). dirname includes a trailing slash. + */ +typedef void fill_ref_dir_fn(struct ref_store *ref_store, + struct ref_dir *dir, const char *dirname); + +struct ref_cache { + struct ref_entry *root; + + /* A pointer to the ref_store whose cache this is: */ + struct ref_store *ref_store; + + /* + * Function used (if necessary) to lazily-fill cache. May be + * NULL. + */ + fill_ref_dir_fn *fill_ref_dir; +}; + +/* + * Information used (along with the information in ref_entry) to + * describe a single cached reference. This data structure only + * occurs embedded in a union in struct ref_entry, and only when + * (ref_entry->flag & REF_DIR) is zero. + */ +struct ref_value { + /* + * The name of the object to which this reference resolves + * (which may be a tag object). If REF_ISBROKEN, this is + * null. If REF_ISSYMREF, then this is the name of the object + * referred to by the last reference in the symlink chain. + */ + struct object_id oid; +}; + +/* + * Information used (along with the information in ref_entry) to + * describe a level in the hierarchy of references. This data + * structure only occurs embedded in a union in struct ref_entry, and + * only when (ref_entry.flag & REF_DIR) is set. In that case, + * (ref_entry.flag & REF_INCOMPLETE) determines whether the references + * in the directory have already been read: + * + * (ref_entry.flag & REF_INCOMPLETE) unset -- a directory of loose + * or packed references, already read. + * + * (ref_entry.flag & REF_INCOMPLETE) set -- a directory of loose + * references that hasn't been read yet (nor has any of its + * subdirectories). + * + * Entries within a directory are stored within a growable array of + * pointers to ref_entries (entries, nr, alloc). Entries 0 <= i < + * sorted are sorted by their component name in strcmp() order and the + * remaining entries are unsorted. + * + * Loose references are read lazily, one directory at a time. When a + * directory of loose references is read, then all of the references + * in that directory are stored, and REF_INCOMPLETE stubs are created + * for any subdirectories, but the subdirectories themselves are not + * read. The reading is triggered by get_ref_dir(). + */ +struct ref_dir { + int nr, alloc; + + /* + * Entries with index 0 <= i < sorted are sorted by name. New + * entries are appended to the list unsorted, and are sorted + * only when required; thus we avoid the need to sort the list + * after the addition of every reference. + */ + int sorted; + + /* The ref_cache containing this entry: */ + struct ref_cache *cache; + + struct ref_entry **entries; +}; + +/* + * Bit values for ref_entry::flag. REF_ISSYMREF=0x01, + * REF_ISPACKED=0x02, REF_ISBROKEN=0x04 and REF_BAD_NAME=0x08 are + * public values; see refs.h. + */ + +/* ref_entry represents a directory of references */ +#define REF_DIR 0x10 + +/* + * Entry has not yet been read from disk (used only for REF_DIR + * entries representing loose references) + */ +#define REF_INCOMPLETE 0x20 + +/* + * A ref_entry represents either a reference or a "subdirectory" of + * references. + * + * Each directory in the reference namespace is represented by a + * ref_entry with (flags & REF_DIR) set and containing a subdir member + * that holds the entries in that directory that have been read so + * far. If (flags & REF_INCOMPLETE) is set, then the directory and + * its subdirectories haven't been read yet. REF_INCOMPLETE is only + * used for loose reference directories. + * + * References are represented by a ref_entry with (flags & REF_DIR) + * unset and a value member that describes the reference's value. The + * flag member is at the ref_entry level, but it is also needed to + * interpret the contents of the value field (in other words, a + * ref_value object is not very much use without the enclosing + * ref_entry). + * + * Reference names cannot end with slash and directories' names are + * always stored with a trailing slash (except for the top-level + * directory, which is always denoted by ""). This has two nice + * consequences: (1) when the entries in each subdir are sorted + * lexicographically by name (as they usually are), the references in + * a whole tree can be generated in lexicographic order by traversing + * the tree in left-to-right, depth-first order; (2) the names of + * references and subdirectories cannot conflict, and therefore the + * presence of an empty subdirectory does not block the creation of a + * similarly-named reference. (The fact that reference names with the + * same leading components can conflict *with each other* is a + * separate issue that is regulated by refs_verify_refname_available().) + * + * Please note that the name field contains the fully-qualified + * reference (or subdirectory) name. Space could be saved by only + * storing the relative names. But that would require the full names + * to be generated on the fly when iterating in do_for_each_ref(), and + * would break callback functions, who have always been able to assume + * that the name strings that they are passed will not be freed during + * the iteration. + */ +struct ref_entry { + unsigned char flag; /* ISSYMREF? ISPACKED? */ + union { + struct ref_value value; /* if not (flags&REF_DIR) */ + struct ref_dir subdir; /* if (flags&REF_DIR) */ + } u; + /* + * The full name of the reference (e.g., "refs/heads/master") + * or the full name of the directory with a trailing slash + * (e.g., "refs/heads/"): + */ + char name[FLEX_ARRAY]; +}; + +/* + * Return the index of the entry with the given refname from the + * ref_dir (non-recursively), sorting dir if necessary. Return -1 if + * no such entry is found. dir must already be complete. + */ +int search_ref_dir(struct ref_dir *dir, const char *refname, size_t len); + +struct ref_dir *get_ref_dir(struct ref_entry *entry); + +/* + * Create a struct ref_entry object for the specified dirname. + * dirname is the name of the directory with a trailing slash (e.g., + * "refs/heads/") or "" for the top-level directory. + */ +struct ref_entry *create_dir_entry(struct ref_cache *cache, + const char *dirname, size_t len); + +struct ref_entry *create_ref_entry(const char *refname, + const struct object_id *oid, int flag); + +/* + * Return a pointer to a new `ref_cache`. Its top-level starts out + * marked incomplete. If `fill_ref_dir` is non-NULL, it is the + * function called to fill in incomplete directories in the + * `ref_cache` when they are accessed. If it is NULL, then the whole + * `ref_cache` must be filled (including clearing its directories' + * `REF_INCOMPLETE` bits) before it is used, and `refs` can be NULL, + * too. + */ +struct ref_cache *create_ref_cache(struct ref_store *refs, + fill_ref_dir_fn *fill_ref_dir); + +/* + * Free the `ref_cache` and all of its associated data. + */ +void free_ref_cache(struct ref_cache *cache); + +/* + * Add a ref_entry to the end of dir (unsorted). Entry is always + * stored directly in dir; no recursion into subdirectories is + * done. + */ +void add_entry_to_dir(struct ref_dir *dir, struct ref_entry *entry); + +/* + * Find the value entry with the given name in dir, sorting ref_dirs + * and recursing into subdirectories as necessary. If the name is not + * found or it corresponds to a directory entry, return NULL. + */ +struct ref_entry *find_ref_entry(struct ref_dir *dir, const char *refname); + +/* + * Start iterating over references in `cache`. If `prefix` is + * specified, only include references whose names start with that + * prefix. If `prime_dir` is true, then fill any incomplete + * directories before beginning the iteration. The output is ordered + * by refname. + */ +struct ref_iterator *cache_ref_iterator_begin(struct ref_cache *cache, + const char *prefix, + struct repository *repo, + int prime_dir); + +#endif /* REFS_REF_CACHE_H */ diff --git a/refs/refs-internal.h b/refs/refs-internal.h new file mode 100644 index 0000000..69f93b0 --- /dev/null +++ b/refs/refs-internal.h @@ -0,0 +1,737 @@ +#ifndef REFS_REFS_INTERNAL_H +#define REFS_REFS_INTERNAL_H + +#include "cache.h" +#include "refs.h" +#include "iterator.h" + +struct ref_transaction; + +/* + * Data structures and functions for the internal use of the refs + * module. Code outside of the refs module should use only the public + * functions defined in "refs.h", and should *not* include this file. + */ + +/* + * The following flags can appear in `ref_update::flags`. Their + * numerical values must not conflict with those of REF_NO_DEREF and + * REF_FORCE_CREATE_REFLOG, which are also stored in + * `ref_update::flags`. + */ + +/* + * The reference should be updated to new_oid. + */ +#define REF_HAVE_NEW (1 << 2) + +/* + * The current reference's value should be checked to make sure that + * it agrees with old_oid. + */ +#define REF_HAVE_OLD (1 << 3) + +/* + * Used as a flag in ref_update::flags when we want to log a ref + * update but not actually perform it. This is used when a symbolic + * ref update is split up. + */ +#define REF_LOG_ONLY (1 << 7) + +/* + * Return the length of time to retry acquiring a loose reference lock + * before giving up, in milliseconds: + */ +long get_files_ref_lock_timeout_ms(void); + +/* + * Return true iff refname is minimally safe. "Safe" here means that + * deleting a loose reference by this name will not do any damage, for + * example by causing a file that is not a reference to be deleted. + * This function does not check that the reference name is legal; for + * that, use check_refname_format(). + * + * A refname that starts with "refs/" is considered safe iff it + * doesn't contain any "." or ".." components or consecutive '/' + * characters, end with '/', or (on Windows) contain any '\' + * characters. Names that do not start with "refs/" are considered + * safe iff they consist entirely of upper case characters and '_' + * (like "HEAD" and "MERGE_HEAD" but not "config" or "FOO/BAR"). + */ +int refname_is_safe(const char *refname); + +/* + * Helper function: return true if refname, which has the specified + * oid and flags, can be resolved to an object in the database. If the + * referred-to object does not exist, emit a warning and return false. + */ +int ref_resolves_to_object(const char *refname, + struct repository *repo, + const struct object_id *oid, + unsigned int flags); + +enum peel_status { + /* object was peeled successfully: */ + PEEL_PEELED = 0, + + /* + * object cannot be peeled because the named object (or an + * object referred to by a tag in the peel chain), does not + * exist. + */ + PEEL_INVALID = -1, + + /* object cannot be peeled because it is not a tag: */ + PEEL_NON_TAG = -2, + + /* ref_entry contains no peeled value because it is a symref: */ + PEEL_IS_SYMREF = -3, + + /* + * ref_entry cannot be peeled because it is broken (i.e., the + * symbolic reference cannot even be resolved to an object + * name): + */ + PEEL_BROKEN = -4 +}; + +/* + * Peel the named object; i.e., if the object is a tag, resolve the + * tag recursively until a non-tag is found. If successful, store the + * result to oid and return PEEL_PEELED. If the object is not a tag + * or is not valid, return PEEL_NON_TAG or PEEL_INVALID, respectively, + * and leave oid unchanged. + */ +enum peel_status peel_object(const struct object_id *name, struct object_id *oid); + +/** + * Information needed for a single ref update. Set new_oid to the new + * value or to null_oid to delete the ref. To check the old value + * while the ref is locked, set (flags & REF_HAVE_OLD) and set old_oid + * to the old value, or to null_oid to ensure the ref does not exist + * before update. + */ +struct ref_update { + /* + * If (flags & REF_HAVE_NEW), set the reference to this value + * (or delete it, if `new_oid` is `null_oid`). + */ + struct object_id new_oid; + + /* + * If (flags & REF_HAVE_OLD), check that the reference + * previously had this value (or didn't previously exist, if + * `old_oid` is `null_oid`). + */ + struct object_id old_oid; + + /* + * One or more of REF_NO_DEREF, REF_FORCE_CREATE_REFLOG, + * REF_HAVE_NEW, REF_HAVE_OLD, or backend-specific flags. + */ + unsigned int flags; + + void *backend_data; + unsigned int type; + char *msg; + + /* + * If this ref_update was split off of a symref update via + * split_symref_update(), then this member points at that + * update. This is used for two purposes: + * 1. When reporting errors, we report the refname under which + * the update was originally requested. + * 2. When we read the old value of this reference, we + * propagate it back to its parent update for recording in + * the latter's reflog. + */ + struct ref_update *parent_update; + + const char refname[FLEX_ARRAY]; +}; + +int refs_read_raw_ref(struct ref_store *ref_store, const char *refname, + struct object_id *oid, struct strbuf *referent, + unsigned int *type, int *failure_errno); + +/* + * Write an error to `err` and return a nonzero value iff the same + * refname appears multiple times in `refnames`. `refnames` must be + * sorted on entry to this function. + */ +int ref_update_reject_duplicates(struct string_list *refnames, + struct strbuf *err); + +/* + * Add a ref_update with the specified properties to transaction, and + * return a pointer to the new object. This function does not verify + * that refname is well-formed. new_oid and old_oid are only + * dereferenced if the REF_HAVE_NEW and REF_HAVE_OLD bits, + * respectively, are set in flags. + */ +struct ref_update *ref_transaction_add_update( + struct ref_transaction *transaction, + const char *refname, unsigned int flags, + const struct object_id *new_oid, + const struct object_id *old_oid, + const char *msg); + +/* + * Transaction states. + * + * OPEN: The transaction is initialized and new updates can still be + * added to it. An OPEN transaction can be prepared, + * committed, freed, or aborted (freeing and aborting an open + * transaction are equivalent). + * + * PREPARED: ref_transaction_prepare(), which locks all of the + * references involved in the update and checks that the + * update has no errors, has been called successfully for the + * transaction. A PREPARED transaction can be committed or + * aborted. + * + * CLOSED: The transaction is no longer active. A transaction becomes + * CLOSED if there is a failure while building the transaction + * or if a transaction is committed or aborted. A CLOSED + * transaction can only be freed. + */ +enum ref_transaction_state { + REF_TRANSACTION_OPEN = 0, + REF_TRANSACTION_PREPARED = 1, + REF_TRANSACTION_CLOSED = 2 +}; + +/* + * Data structure for holding a reference transaction, which can + * consist of checks and updates to multiple references, carried out + * as atomically as possible. This structure is opaque to callers. + */ +struct ref_transaction { + struct ref_store *ref_store; + struct ref_update **updates; + size_t alloc; + size_t nr; + enum ref_transaction_state state; + void *backend_data; +}; + +/* + * Check for entries in extras that are within the specified + * directory, where dirname is a reference directory name including + * the trailing slash (e.g., "refs/heads/foo/"). Ignore any + * conflicting references that are found in skip. If there is a + * conflicting reference, return its name. + * + * extras and skip must be sorted lists of reference names. Either one + * can be NULL, signifying the empty list. + */ +const char *find_descendant_ref(const char *dirname, + const struct string_list *extras, + const struct string_list *skip); + +/* We allow "recursive" symbolic refs. Only within reason, though */ +#define SYMREF_MAXDEPTH 5 + +/* + * These flags are passed to refs_ref_iterator_begin() (and do_for_each_ref(), + * which feeds it). + */ +enum do_for_each_ref_flags { + /* + * Include broken references in a do_for_each_ref*() iteration, which + * would normally be omitted. This includes both refs that point to + * missing objects (a true repository corruption), ones with illegal + * names (which we prefer not to expose to callers), as well as + * dangling symbolic refs (i.e., those that point to a non-existent + * ref; this is not a corruption, but as they have no valid oid, we + * omit them from normal iteration results). + */ + DO_FOR_EACH_INCLUDE_BROKEN = (1 << 0), + + /* + * Only include per-worktree refs in a do_for_each_ref*() iteration. + * Normally this will be used with a files ref_store, since that's + * where all reference backends will presumably store their + * per-worktree refs. + */ + DO_FOR_EACH_PER_WORKTREE_ONLY = (1 << 1), + + /* + * Omit dangling symrefs from output; this only has an effect with + * INCLUDE_BROKEN, since they are otherwise not included at all. + */ + DO_FOR_EACH_OMIT_DANGLING_SYMREFS = (1 << 2), +}; + +/* + * Reference iterators + * + * A reference iterator encapsulates the state of an in-progress + * iteration over references. Create an instance of `struct + * ref_iterator` via one of the functions in this module. + * + * A freshly-created ref_iterator doesn't yet point at a reference. To + * advance the iterator, call ref_iterator_advance(). If successful, + * this sets the iterator's refname, oid, and flags fields to describe + * the next reference and returns ITER_OK. The data pointed at by + * refname and oid belong to the iterator; if you want to retain them + * after calling ref_iterator_advance() again or calling + * ref_iterator_abort(), you must make a copy. When the iteration has + * been exhausted, ref_iterator_advance() releases any resources + * associated with the iteration, frees the ref_iterator object, and + * returns ITER_DONE. If you want to abort the iteration early, call + * ref_iterator_abort(), which also frees the ref_iterator object and + * any associated resources. If there was an internal error advancing + * to the next entry, ref_iterator_advance() aborts the iteration, + * frees the ref_iterator, and returns ITER_ERROR. + * + * The reference currently being looked at can be peeled by calling + * ref_iterator_peel(). This function is often faster than peel_ref(), + * so it should be preferred when iterating over references. + * + * Putting it all together, a typical iteration looks like this: + * + * int ok; + * struct ref_iterator *iter = ...; + * + * while ((ok = ref_iterator_advance(iter)) == ITER_OK) { + * if (want_to_stop_iteration()) { + * ok = ref_iterator_abort(iter); + * break; + * } + * + * // Access information about the current reference: + * if (!(iter->flags & REF_ISSYMREF)) + * printf("%s is %s\n", iter->refname, oid_to_hex(iter->oid)); + * + * // If you need to peel the reference: + * ref_iterator_peel(iter, &oid); + * } + * + * if (ok != ITER_DONE) + * handle_error(); + */ +struct ref_iterator { + struct ref_iterator_vtable *vtable; + + /* + * Does this `ref_iterator` iterate over references in order + * by refname? + */ + unsigned int ordered : 1; + + const char *refname; + const struct object_id *oid; + unsigned int flags; +}; + +/* + * Advance the iterator to the first or next item and return ITER_OK. + * If the iteration is exhausted, free the resources associated with + * the ref_iterator and return ITER_DONE. On errors, free the iterator + * resources and return ITER_ERROR. It is a bug to use ref_iterator or + * call this function again after it has returned ITER_DONE or + * ITER_ERROR. + */ +int ref_iterator_advance(struct ref_iterator *ref_iterator); + +/* + * If possible, peel the reference currently being viewed by the + * iterator. Return 0 on success. + */ +int ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled); + +/* + * End the iteration before it has been exhausted, freeing the + * reference iterator and any associated resources and returning + * ITER_DONE. If the abort itself failed, return ITER_ERROR. + */ +int ref_iterator_abort(struct ref_iterator *ref_iterator); + +/* + * An iterator over nothing (its first ref_iterator_advance() call + * returns ITER_DONE). + */ +struct ref_iterator *empty_ref_iterator_begin(void); + +/* + * Return true iff ref_iterator is an empty_ref_iterator. + */ +int is_empty_ref_iterator(struct ref_iterator *ref_iterator); + +/* + * Return an iterator that goes over each reference in `refs` for + * which the refname begins with prefix. If trim is non-zero, then + * trim that many characters off the beginning of each refname. + * The output is ordered by refname. + */ +struct ref_iterator *refs_ref_iterator_begin( + struct ref_store *refs, + const char *prefix, int trim, + enum do_for_each_ref_flags flags); + +/* + * A callback function used to instruct merge_ref_iterator how to + * interleave the entries from iter0 and iter1. The function should + * return one of the constants defined in enum iterator_selection. It + * must not advance either of the iterators itself. + * + * The function must be prepared to handle the case that iter0 and/or + * iter1 is NULL, which indicates that the corresponding sub-iterator + * has been exhausted. Its return value must be consistent with the + * current states of the iterators; e.g., it must not return + * ITER_SKIP_1 if iter1 has already been exhausted. + */ +typedef enum iterator_selection ref_iterator_select_fn( + struct ref_iterator *iter0, struct ref_iterator *iter1, + void *cb_data); + +/* + * Iterate over the entries from iter0 and iter1, with the values + * interleaved as directed by the select function. The iterator takes + * ownership of iter0 and iter1 and frees them when the iteration is + * over. A derived class should set `ordered` to 1 or 0 based on + * whether it generates its output in order by reference name. + */ +struct ref_iterator *merge_ref_iterator_begin( + int ordered, + struct ref_iterator *iter0, struct ref_iterator *iter1, + ref_iterator_select_fn *select, void *cb_data); + +/* + * An iterator consisting of the union of the entries from front and + * back. If there are entries common to the two sub-iterators, use the + * one from front. Each iterator must iterate over its entries in + * strcmp() order by refname for this to work. + * + * The new iterator takes ownership of its arguments and frees them + * when the iteration is over. As a convenience to callers, if front + * or back is an empty_ref_iterator, then abort that one immediately + * and return the other iterator directly, without wrapping it. + */ +struct ref_iterator *overlay_ref_iterator_begin( + struct ref_iterator *front, struct ref_iterator *back); + +/* + * Wrap iter0, only letting through the references whose names start + * with prefix. If trim is set, set iter->refname to the name of the + * reference with that many characters trimmed off the front; + * otherwise set it to the full refname. The new iterator takes over + * ownership of iter0 and frees it when iteration is over. It makes + * its own copy of prefix. + * + * As an convenience to callers, if prefix is the empty string and + * trim is zero, this function returns iter0 directly, without + * wrapping it. + * + * The resulting ref_iterator is ordered if iter0 is. + */ +struct ref_iterator *prefix_ref_iterator_begin(struct ref_iterator *iter0, + const char *prefix, + int trim); + +/* Internal implementation of reference iteration: */ + +/* + * Base class constructor for ref_iterators. Initialize the + * ref_iterator part of iter, setting its vtable pointer as specified. + * `ordered` should be set to 1 if the iterator will iterate over + * references in order by refname; otherwise it should be set to 0. + * This is meant to be called only by the initializers of derived + * classes. + */ +void base_ref_iterator_init(struct ref_iterator *iter, + struct ref_iterator_vtable *vtable, + int ordered); + +/* + * Base class destructor for ref_iterators. Destroy the ref_iterator + * part of iter and shallow-free the object. This is meant to be + * called only by the destructors of derived classes. + */ +void base_ref_iterator_free(struct ref_iterator *iter); + +/* Virtual function declarations for ref_iterators: */ + +/* + * backend-specific implementation of ref_iterator_advance. For symrefs, the + * function should set REF_ISSYMREF, and it should also dereference the symref + * to provide the OID referent. It should respect do_for_each_ref_flags + * that were passed to refs_ref_iterator_begin(). + */ +typedef int ref_iterator_advance_fn(struct ref_iterator *ref_iterator); + +/* + * Peels the current ref, returning 0 for success or -1 for failure. + */ +typedef int ref_iterator_peel_fn(struct ref_iterator *ref_iterator, + struct object_id *peeled); + +/* + * Implementations of this function should free any resources specific + * to the derived class, then call base_ref_iterator_free() to clean + * up and free the ref_iterator object. + */ +typedef int ref_iterator_abort_fn(struct ref_iterator *ref_iterator); + +struct ref_iterator_vtable { + ref_iterator_advance_fn *advance; + ref_iterator_peel_fn *peel; + ref_iterator_abort_fn *abort; +}; + +/* + * current_ref_iter is a performance hack: when iterating over + * references using the for_each_ref*() functions, current_ref_iter is + * set to the reference iterator before calling the callback function. + * If the callback function calls peel_ref(), then peel_ref() first + * checks whether the reference to be peeled is the one referred to by + * the iterator (it usually is) and if so, asks the iterator for the + * peeled version of the reference if it is available. This avoids a + * refname lookup in a common case. current_ref_iter is set to NULL + * when the iteration is over. + */ +extern struct ref_iterator *current_ref_iter; + +/* + * The common backend for the for_each_*ref* functions. Call fn for + * each reference in iter. If the iterator itself ever returns + * ITER_ERROR, return -1. If fn ever returns a non-zero value, stop + * the iteration and return that value. Otherwise, return 0. In any + * case, free the iterator when done. This function is basically an + * adapter between the callback style of reference iteration and the + * iterator style. + */ +int do_for_each_repo_ref_iterator(struct repository *r, + struct ref_iterator *iter, + each_repo_ref_fn fn, void *cb_data); + +struct ref_store; + +/* refs backends */ + +/* ref_store_init flags */ +#define REF_STORE_READ (1 << 0) +#define REF_STORE_WRITE (1 << 1) /* can perform update operations */ +#define REF_STORE_ODB (1 << 2) /* has access to object database */ +#define REF_STORE_MAIN (1 << 3) +#define REF_STORE_ALL_CAPS (REF_STORE_READ | \ + REF_STORE_WRITE | \ + REF_STORE_ODB | \ + REF_STORE_MAIN) + +/* + * Initialize the ref_store for the specified gitdir. These functions + * should call base_ref_store_init() to initialize the shared part of + * the ref_store and to record the ref_store for later lookup. + */ +typedef struct ref_store *ref_store_init_fn(struct repository *repo, + const char *gitdir, + unsigned int flags); + +typedef int ref_init_db_fn(struct ref_store *refs, struct strbuf *err); + +typedef int ref_transaction_prepare_fn(struct ref_store *refs, + struct ref_transaction *transaction, + struct strbuf *err); + +typedef int ref_transaction_finish_fn(struct ref_store *refs, + struct ref_transaction *transaction, + struct strbuf *err); + +typedef int ref_transaction_abort_fn(struct ref_store *refs, + struct ref_transaction *transaction, + struct strbuf *err); + +typedef int ref_transaction_commit_fn(struct ref_store *refs, + struct ref_transaction *transaction, + struct strbuf *err); + +typedef int pack_refs_fn(struct ref_store *ref_store, unsigned int flags); +typedef int create_symref_fn(struct ref_store *ref_store, + const char *ref_target, + const char *refs_heads_master, + const char *logmsg); +typedef int delete_refs_fn(struct ref_store *ref_store, const char *msg, + struct string_list *refnames, unsigned int flags); +typedef int rename_ref_fn(struct ref_store *ref_store, + const char *oldref, const char *newref, + const char *logmsg); +typedef int copy_ref_fn(struct ref_store *ref_store, + const char *oldref, const char *newref, + const char *logmsg); + +/* + * Iterate over the references in `ref_store` whose names start with + * `prefix`. `prefix` is matched as a literal string, without regard + * for path separators. If prefix is NULL or the empty string, iterate + * over all references in `ref_store`. The output is ordered by + * refname. + */ +typedef struct ref_iterator *ref_iterator_begin_fn( + struct ref_store *ref_store, + const char *prefix, unsigned int flags); + +/* reflog functions */ + +/* + * Iterate over the references in the specified ref_store that have a + * reflog. The refs are iterated over in arbitrary order. + */ +typedef struct ref_iterator *reflog_iterator_begin_fn( + struct ref_store *ref_store); + +typedef int for_each_reflog_ent_fn(struct ref_store *ref_store, + const char *refname, + each_reflog_ent_fn fn, + void *cb_data); +typedef int for_each_reflog_ent_reverse_fn(struct ref_store *ref_store, + const char *refname, + each_reflog_ent_fn fn, + void *cb_data); +typedef int reflog_exists_fn(struct ref_store *ref_store, const char *refname); +typedef int create_reflog_fn(struct ref_store *ref_store, const char *refname, + struct strbuf *err); +typedef int delete_reflog_fn(struct ref_store *ref_store, const char *refname); +typedef int reflog_expire_fn(struct ref_store *ref_store, + const char *refname, + unsigned int flags, + reflog_expiry_prepare_fn prepare_fn, + reflog_expiry_should_prune_fn should_prune_fn, + reflog_expiry_cleanup_fn cleanup_fn, + void *policy_cb_data); + +/* + * Read a reference from the specified reference store, non-recursively. + * Set type to describe the reference, and: + * + * - If refname is the name of a normal reference, fill in oid + * (leaving referent unchanged). + * + * - If refname is the name of a symbolic reference, write the full + * name of the reference to which it refers (e.g. + * "refs/heads/master") to referent and set the REF_ISSYMREF bit in + * type (leaving oid unchanged). The caller is responsible for + * validating that referent is a valid reference name. + * + * WARNING: refname might be used as part of a filename, so it is + * important from a security standpoint that it be safe in the sense + * of refname_is_safe(). Moreover, for symrefs this function sets + * referent to whatever the repository says, which might not be a + * properly-formatted or even safe reference name. NEITHER INPUT NOR + * OUTPUT REFERENCE NAMES ARE VALIDATED WITHIN THIS FUNCTION. + * + * Return 0 on success, or -1 on failure. If the ref exists but is neither a + * symbolic ref nor an object ID, it is broken. In this case set REF_ISBROKEN in + * type, and return -1 (failure_errno should not be ENOENT) + * + * failure_errno provides errno codes that are interpreted beyond error + * reporting. The following error codes have special meaning: + * * ENOENT: the ref doesn't exist + * * EISDIR: ref name is a directory + * * ENOTDIR: ref prefix is not a directory + * + * Backend-specific flags might be set in type as well, regardless of + * outcome. + * + * It is OK for refname to point into referent. If so: + * + * - if the function succeeds with REF_ISSYMREF, referent will be + * overwritten and the memory formerly pointed to by it might be + * changed or even freed. + * + * - in all other cases, referent will be untouched, and therefore + * refname will still be valid and unchanged. + */ +typedef int read_raw_ref_fn(struct ref_store *ref_store, const char *refname, + struct object_id *oid, struct strbuf *referent, + unsigned int *type, int *failure_errno); + +/* + * Read a symbolic reference from the specified reference store. This function + * is optional: if not implemented by a backend, then `read_raw_ref_fn` is used + * to read the symbolcic reference instead. It is intended to be implemented + * only in case the backend can optimize the reading of symbolic references. + * + * Return 0 on success, or -1 on failure. `referent` will be set to the target + * of the symbolic reference on success. This function explicitly does not + * distinguish between error cases and the reference not being a symbolic + * reference to allow backends to optimize this operation in case symbolic and + * non-symbolic references are treated differently. + */ +typedef int read_symbolic_ref_fn(struct ref_store *ref_store, const char *refname, + struct strbuf *referent); + +struct ref_storage_be { + struct ref_storage_be *next; + const char *name; + ref_store_init_fn *init; + ref_init_db_fn *init_db; + + ref_transaction_prepare_fn *transaction_prepare; + ref_transaction_finish_fn *transaction_finish; + ref_transaction_abort_fn *transaction_abort; + ref_transaction_commit_fn *initial_transaction_commit; + + pack_refs_fn *pack_refs; + create_symref_fn *create_symref; + delete_refs_fn *delete_refs; + rename_ref_fn *rename_ref; + copy_ref_fn *copy_ref; + + ref_iterator_begin_fn *iterator_begin; + read_raw_ref_fn *read_raw_ref; + read_symbolic_ref_fn *read_symbolic_ref; + + reflog_iterator_begin_fn *reflog_iterator_begin; + for_each_reflog_ent_fn *for_each_reflog_ent; + for_each_reflog_ent_reverse_fn *for_each_reflog_ent_reverse; + reflog_exists_fn *reflog_exists; + create_reflog_fn *create_reflog; + delete_reflog_fn *delete_reflog; + reflog_expire_fn *reflog_expire; +}; + +extern struct ref_storage_be refs_be_files; +extern struct ref_storage_be refs_be_packed; + +/* + * A representation of the reference store for the main repository or + * a submodule. The ref_store instances for submodules are kept in a + * hash map; see get_submodule_ref_store() for more info. + */ +struct ref_store { + /* The backend describing this ref_store's storage scheme: */ + const struct ref_storage_be *be; + + struct repository *repo; + + /* + * The gitdir that this ref_store applies to. Note that this is not + * necessarily repo->gitdir if the repo has multiple worktrees. + */ + char *gitdir; +}; + +/* + * Parse contents of a loose ref file. *failure_errno maybe be set to EINVAL for + * invalid contents. + */ +int parse_loose_ref_contents(const char *buf, struct object_id *oid, + struct strbuf *referent, unsigned int *type, + int *failure_errno); + +/* + * Fill in the generic part of refs and add it to our collection of + * reference stores. + */ +void base_ref_store_init(struct ref_store *refs, struct repository *repo, + const char *path, const struct ref_storage_be *be); + +/* + * Support GIT_TRACE_REFS by optionally wrapping the given ref_store instance. + */ +struct ref_store *maybe_debug_wrap_ref_store(const char *gitdir, struct ref_store *store); + +#endif /* REFS_REFS_INTERNAL_H */ |