diff options
Diffstat (limited to 'refs')
| -rw-r--r-- | refs/files-backend.c | 1587 | ||||
| -rw-r--r-- | refs/iterator.c | 384 | ||||
| -rw-r--r-- | refs/refs-internal.h | 321 |
3 files changed, 1819 insertions, 473 deletions
diff --git a/refs/files-backend.c b/refs/files-backend.c index 1f38076411..2455564352 100644 --- a/refs/files-backend.c +++ b/refs/files-backend.c @@ -1,13 +1,14 @@ #include "../cache.h" #include "../refs.h" #include "refs-internal.h" +#include "../iterator.h" +#include "../dir-iterator.h" #include "../lockfile.h" #include "../object.h" #include "../dir.h" struct ref_lock { char *ref_name; - char *orig_ref_name; struct lock_file *lk; struct object_id old_oid; }; @@ -514,68 +515,36 @@ static void sort_ref_dir(struct ref_dir *dir) } /* - * Return true iff the reference described by entry can be resolved to - * an object in the database. Emit a warning if the referred-to - * object does not exist. + * 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. */ -static int ref_resolves_to_object(struct ref_entry *entry) +static int ref_resolves_to_object(const char *refname, + const struct object_id *oid, + unsigned int flags) { - if (entry->flag & REF_ISBROKEN) + if (flags & REF_ISBROKEN) return 0; - if (!has_sha1_file(entry->u.value.oid.hash)) { - error("%s does not point to a valid object!", entry->name); + if (!has_sha1_file(oid->hash)) { + error("%s does not point to a valid object!", refname); return 0; } return 1; } /* - * current_ref is a performance hack: when iterating over references - * using the for_each_ref*() functions, current_ref is set to the - * current reference's entry 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 current reference - * (it usually is) and if so, returns that reference's peeled version - * if it is available. This avoids a refname lookup in a common case. - */ -static struct ref_entry *current_ref; - -typedef int each_ref_entry_fn(struct ref_entry *entry, void *cb_data); - -struct ref_entry_cb { - const char *base; - int trim; - int flags; - each_ref_fn *fn; - void *cb_data; -}; - -/* - * Handle one reference in a do_for_each_ref*()-style iteration, - * calling an each_ref_fn for each entry. + * Return true if the reference described by entry can be resolved to + * an object in the database; otherwise, emit a warning and return + * false. */ -static int do_one_ref(struct ref_entry *entry, void *cb_data) +static int entry_resolves_to_object(struct ref_entry *entry) { - struct ref_entry_cb *data = cb_data; - struct ref_entry *old_current_ref; - int retval; - - if (!starts_with(entry->name, data->base)) - return 0; - - if (!(data->flags & DO_FOR_EACH_INCLUDE_BROKEN) && - !ref_resolves_to_object(entry)) - return 0; - - /* Store the old value, in case this is a recursive call: */ - old_current_ref = current_ref; - current_ref = entry; - retval = data->fn(entry->name + data->trim, &entry->u.value.oid, - entry->flag, data->cb_data); - current_ref = old_current_ref; - return retval; + return ref_resolves_to_object(entry->name, + &entry->u.value.oid, entry->flag); } +typedef int each_ref_entry_fn(struct ref_entry *entry, void *cb_data); + /* * Call fn for each reference in dir that has index in the range * offset <= index < dir->nr. Recurse into subdirectories that are in @@ -605,78 +574,6 @@ static int do_for_each_entry_in_dir(struct ref_dir *dir, int offset, } /* - * Call fn for each reference in the union of dir1 and dir2, in order - * by refname. Recurse into subdirectories. If a value entry appears - * in both dir1 and dir2, then only process the version that is in - * dir2. The input dirs must already be sorted, but subdirs will be - * sorted as needed. fn is called for all references, including - * broken ones. - */ -static int do_for_each_entry_in_dirs(struct ref_dir *dir1, - struct ref_dir *dir2, - each_ref_entry_fn fn, void *cb_data) -{ - int retval; - int i1 = 0, i2 = 0; - - assert(dir1->sorted == dir1->nr); - assert(dir2->sorted == dir2->nr); - while (1) { - struct ref_entry *e1, *e2; - int cmp; - if (i1 == dir1->nr) { - return do_for_each_entry_in_dir(dir2, i2, fn, cb_data); - } - if (i2 == dir2->nr) { - return do_for_each_entry_in_dir(dir1, i1, fn, cb_data); - } - e1 = dir1->entries[i1]; - e2 = dir2->entries[i2]; - cmp = strcmp(e1->name, e2->name); - if (cmp == 0) { - if ((e1->flag & REF_DIR) && (e2->flag & REF_DIR)) { - /* Both are directories; descend them in parallel. */ - struct ref_dir *subdir1 = get_ref_dir(e1); - struct ref_dir *subdir2 = get_ref_dir(e2); - sort_ref_dir(subdir1); - sort_ref_dir(subdir2); - retval = do_for_each_entry_in_dirs( - subdir1, subdir2, fn, cb_data); - i1++; - i2++; - } else if (!(e1->flag & REF_DIR) && !(e2->flag & REF_DIR)) { - /* Both are references; ignore the one from dir1. */ - retval = fn(e2, cb_data); - i1++; - i2++; - } else { - die("conflict between reference and directory: %s", - e1->name); - } - } else { - struct ref_entry *e; - if (cmp < 0) { - e = e1; - i1++; - } else { - e = e2; - i2++; - } - if (e->flag & REF_DIR) { - struct ref_dir *subdir = get_ref_dir(e); - sort_ref_dir(subdir); - retval = do_for_each_entry_in_dir( - subdir, 0, fn, cb_data); - } else { - retval = fn(e, cb_data); - } - } - if (retval) - return retval; - } -} - -/* * Load all of the refs from the dir into our in-memory cache. 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 @@ -692,6 +589,153 @@ static void prime_ref_dir(struct ref_dir *dir) } } +/* + * 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; + + /* + * 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; + + /* + * 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; +}; + +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; + + 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 (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->index = -1; + } else { + iter->base.refname = entry->name; + iter->base.oid = &entry->u.value.oid; + iter->base.flags = entry->flag; + return ITER_OK; + } + } +} + +static enum peel_status peel_entry(struct ref_entry *entry, int repeel); + +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; + struct cache_ref_iterator_level *level; + struct ref_entry *entry; + + level = &iter->levels[iter->levels_nr - 1]; + + if (level->index == -1) + die("BUG: peel called before advance for cache iterator"); + + entry = level->dir->entries[level->index]; + + if (peel_entry(entry, 0)) + return -1; + hashcpy(peeled->hash, entry->u.value.peeled.hash); + return 0; +} + +static int cache_ref_iterator_abort(struct ref_iterator *ref_iterator) +{ + struct cache_ref_iterator *iter = + (struct cache_ref_iterator *)ref_iterator; + + free(iter->levels); + base_ref_iterator_free(ref_iterator); + return ITER_DONE; +} + +static struct ref_iterator_vtable cache_ref_iterator_vtable = { + cache_ref_iterator_advance, + cache_ref_iterator_peel, + cache_ref_iterator_abort +}; + +static struct ref_iterator *cache_ref_iterator_begin(struct ref_dir *dir) +{ + struct cache_ref_iterator *iter; + struct ref_iterator *ref_iterator; + struct cache_ref_iterator_level *level; + + iter = xcalloc(1, sizeof(*iter)); + ref_iterator = &iter->base; + base_ref_iterator_init(ref_iterator, &cache_ref_iterator_vtable); + ALLOC_GROW(iter->levels, 10, iter->levels_alloc); + + iter->levels_nr = 1; + level = &iter->levels[0]; + level->index = -1; + level->dir = dir; + + return ref_iterator; +} + struct nonmatching_ref_data { const struct string_list *skip; const char *conflicting_refname; @@ -955,15 +999,26 @@ static struct ref_cache *lookup_ref_cache(const char *submodule) /* * Return a pointer to a ref_cache for the specified submodule. For - * the main repository, use submodule==NULL. The returned structure - * will be allocated and initialized but not necessarily populated; it - * should not be freed. + * the main repository, use submodule==NULL; such a call cannot fail. + * For a submodule, the submodule must exist and be a nonbare + * repository, otherwise return NULL. + * + * The returned structure will be allocated and initialized but not + * necessarily populated; it should not be freed. */ static struct ref_cache *get_ref_cache(const char *submodule) { struct ref_cache *refs = lookup_ref_cache(submodule); - if (!refs) - refs = create_ref_cache(submodule); + + if (!refs) { + struct strbuf submodule_sb = STRBUF_INIT; + + strbuf_addstr(&submodule_sb, submodule); + if (is_nonbare_repository_dir(&submodule_sb)) + refs = create_ref_cache(submodule); + strbuf_release(&submodule_sb); + } + return refs; } @@ -1342,13 +1397,10 @@ int resolve_gitlink_ref(const char *path, const char *refname, unsigned char *sh return -1; strbuf_add(&submodule, path, len); - refs = lookup_ref_cache(submodule.buf); + refs = get_ref_cache(submodule.buf); if (!refs) { - if (!is_nonbare_repository_dir(&submodule)) { - strbuf_release(&submodule); - return -1; - } - refs = create_ref_cache(submodule.buf); + strbuf_release(&submodule); + return -1; } strbuf_release(&submodule); @@ -1388,38 +1440,8 @@ static int resolve_missing_loose_ref(const char *refname, return -1; } -/* - * Read a raw ref from the filesystem or packed refs file. - * - * If the ref is a sha1, fill in sha1 and return 0. - * - * If the ref is symbolic, fill in *symref with the referrent - * (e.g. "refs/heads/master") and return 0. The caller is responsible - * for validating the referrent. Set REF_ISSYMREF in flags. - * - * If the ref doesn't exist, set errno to ENOENT and return -1. - * - * If the ref exists but is neither a symbolic ref nor a sha1, it is - * broken. Set REF_ISBROKEN in flags, set errno to EINVAL, and return - * -1. - * - * If there is another error reading the ref, set errno appropriately and - * return -1. - * - * Backend-specific flags might be set in flags as well, regardless of - * outcome. - * - * sb_path is workspace: the caller should allocate and free it. - * - * It is OK for refname to point into symref. In this case: - * - if the function succeeds with REF_ISSYMREF, symref will be - * overwritten and the memory pointed to by refname might be changed - * or even freed. - * - in all other cases, symref will be untouched, and therefore - * refname will still be valid and unchanged. - */ int read_raw_ref(const char *refname, unsigned char *sha1, - struct strbuf *symref, unsigned int *flags) + struct strbuf *referent, unsigned int *type) { struct strbuf sb_contents = STRBUF_INIT; struct strbuf sb_path = STRBUF_INIT; @@ -1429,7 +1451,9 @@ int read_raw_ref(const char *refname, unsigned char *sha1, int fd; int ret = -1; int save_errno; + int remaining_retries = 3; + *type = 0; strbuf_reset(&sb_path); strbuf_git_path(&sb_path, "%s", refname); path = sb_path.buf; @@ -1443,12 +1467,18 @@ stat_ref: * <-> 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) { if (errno != ENOENT) goto out; - if (resolve_missing_loose_ref(refname, sha1, flags)) { + if (resolve_missing_loose_ref(refname, sha1, type)) { errno = ENOENT; goto out; } @@ -1468,16 +1498,30 @@ stat_ref: } if (starts_with(sb_contents.buf, "refs/") && !check_refname_format(sb_contents.buf, 0)) { - strbuf_swap(&sb_contents, symref); - *flags |= REF_ISSYMREF; + 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)) { - errno = EISDIR; + /* + * Even though there is a directory where the loose + * ref is supposed to be, there could still be a + * packed ref: + */ + if (resolve_missing_loose_ref(refname, sha1, type)) { + errno = EISDIR; + goto out; + } + ret = 0; goto out; } @@ -1487,7 +1531,7 @@ stat_ref: */ fd = open(path, O_RDONLY); if (fd < 0) { - if (errno == ENOENT) + if (errno == ENOENT && !S_ISLNK(st.st_mode)) /* inconsistent with lstat; retry */ goto stat_ref; else @@ -1508,9 +1552,9 @@ stat_ref: while (isspace(*buf)) buf++; - strbuf_reset(symref); - strbuf_addstr(symref, buf); - *flags |= REF_ISSYMREF; + strbuf_reset(referent); + strbuf_addstr(referent, buf); + *type |= REF_ISSYMREF; ret = 0; goto out; } @@ -1521,7 +1565,7 @@ stat_ref: */ if (get_sha1_hex(buf, sha1) || (buf[40] != '\0' && !isspace(buf[40]))) { - *flags |= REF_ISBROKEN; + *type |= REF_ISBROKEN; errno = EINVAL; goto out; } @@ -1536,6 +1580,241 @@ out: return ret; } +static void unlock_ref(struct ref_lock *lock) +{ + /* Do not free lock->lk -- atexit() still looks at them */ + if (lock->lk) + 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 verify_refname_available_dir() for this check. + * + * If mustexist is not set and the reference is not found or is + * broken, lock the reference anyway but clear sha1. + * + * 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 verify_refname_available_dir() 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(const char *refname, int mustexist, + const struct string_list *extras, + const struct string_list *skip, + 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; + + assert(err); + *type = 0; + + /* First lock the file so it can't change out from under us. */ + + *lock_p = lock = xcalloc(1, sizeof(*lock)); + + lock->ref_name = xstrdup(refname); + strbuf_git_path(&ref_file, "%s", 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 (verify_refname_available(refname, extras, skip, 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 + * verify_refname_available_dir() 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 (!lock->lk) + lock->lk = xcalloc(1, sizeof(struct lock_file)); + + if (hold_lock_file_for_update(lock->lk, ref_file.buf, LOCK_NO_DEREF) < 0) { + if (errno == 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, errno, err); + goto error_return; + } + } + + /* + * Now we hold the lock and can read the reference without + * fear that its value will change. + */ + + if (read_raw_ref(refname, lock->old_oid.hash, referent, type)) { + if (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 (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 (verify_refname_available_dir( + refname, extras, skip, + get_loose_refs(&ref_cache), + 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 (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(errno)); + goto error_return; + } + + /* + * 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 (verify_refname_available_dir( + refname, extras, skip, + get_packed_refs(&ref_cache), + err)) { + goto error_return; + } + } + + ret = 0; + goto out; + +error_return: + unlock_ref(lock); + *lock_p = NULL; + +out: + strbuf_release(&ref_file); + return ret; +} + /* * Peel the entry (if possible) and return its new peel_status. If * repeel is true, re-peel the entry even if there is an old peeled @@ -1576,11 +1855,12 @@ int peel_ref(const char *refname, unsigned char *sha1) int flag; unsigned char base[20]; - if (current_ref && (current_ref->name == refname - || !strcmp(current_ref->name, refname))) { - if (peel_entry(current_ref, 0)) + if (current_ref_iter && current_ref_iter->refname == refname) { + struct object_id peeled; + + if (ref_iterator_peel(current_ref_iter, &peeled)) return -1; - hashcpy(sha1, current_ref->u.value.peeled.hash); + hashcpy(sha1, peeled.hash); return 0; } @@ -1608,100 +1888,137 @@ int peel_ref(const char *refname, unsigned char *sha1) return peel_object(base, sha1); } -/* - * Call fn for each reference in the specified ref_cache, omitting - * references not in the containing_dir of base. fn is called for all - * references, including broken ones. If fn ever returns a non-zero - * value, stop the iteration and return that value; otherwise, return - * 0. - */ -static int do_for_each_entry(struct ref_cache *refs, const char *base, - each_ref_entry_fn fn, void *cb_data) -{ +struct files_ref_iterator { + struct ref_iterator base; + struct packed_ref_cache *packed_ref_cache; - struct ref_dir *loose_dir; - struct ref_dir *packed_dir; - int retval = 0; + struct ref_iterator *iter0; + unsigned int flags; +}; - /* - * We must make sure that all loose refs are read before accessing the - * packed-refs file; this avoids a race condition in which loose refs - * are migrated to the packed-refs file by a simultaneous process, but - * our in-memory view is from before the migration. get_packed_ref_cache() - * takes care of making sure our view is up to date with what is on - * disk. - */ - loose_dir = get_loose_refs(refs); - if (base && *base) { - loose_dir = find_containing_dir(loose_dir, base, 0); - } - if (loose_dir) - prime_ref_dir(loose_dir); +static int files_ref_iterator_advance(struct ref_iterator *ref_iterator) +{ + struct files_ref_iterator *iter = + (struct files_ref_iterator *)ref_iterator; + int ok; - packed_ref_cache = get_packed_ref_cache(refs); - acquire_packed_ref_cache(packed_ref_cache); - packed_dir = get_packed_ref_dir(packed_ref_cache); - if (base && *base) { - packed_dir = find_containing_dir(packed_dir, base, 0); - } - - if (packed_dir && loose_dir) { - sort_ref_dir(packed_dir); - sort_ref_dir(loose_dir); - retval = do_for_each_entry_in_dirs( - packed_dir, loose_dir, fn, cb_data); - } else if (packed_dir) { - sort_ref_dir(packed_dir); - retval = do_for_each_entry_in_dir( - packed_dir, 0, fn, cb_data); - } else if (loose_dir) { - sort_ref_dir(loose_dir); - retval = do_for_each_entry_in_dir( - loose_dir, 0, fn, cb_data); + while ((ok = ref_iterator_advance(iter->iter0)) == ITER_OK) { + if (!(iter->flags & DO_FOR_EACH_INCLUDE_BROKEN) && + !ref_resolves_to_object(iter->iter0->refname, + 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; } - release_packed_ref_cache(packed_ref_cache); - return retval; + iter->iter0 = NULL; + if (ref_iterator_abort(ref_iterator) != ITER_DONE) + ok = ITER_ERROR; + + return ok; } -/* - * Call fn for each reference in the specified ref_cache for which the - * refname begins with base. If trim is non-zero, then trim that many - * characters off the beginning of each refname before passing the - * refname to fn. flags can be DO_FOR_EACH_INCLUDE_BROKEN to include - * broken references in the iteration. If fn ever returns a non-zero - * value, stop the iteration and return that value; otherwise, return - * 0. - */ -int do_for_each_ref(const char *submodule, const char *base, - each_ref_fn fn, int trim, int flags, void *cb_data) +static int files_ref_iterator_peel(struct ref_iterator *ref_iterator, + struct object_id *peeled) { - struct ref_entry_cb data; - struct ref_cache *refs; + 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); + + release_packed_ref_cache(iter->packed_ref_cache); + base_ref_iterator_free(ref_iterator); + return ok; +} - refs = get_ref_cache(submodule); - data.base = base; - data.trim = trim; - data.flags = flags; - data.fn = fn; - data.cb_data = cb_data; +static struct ref_iterator_vtable files_ref_iterator_vtable = { + files_ref_iterator_advance, + files_ref_iterator_peel, + files_ref_iterator_abort +}; + +struct ref_iterator *files_ref_iterator_begin( + const char *submodule, + const char *prefix, unsigned int flags) +{ + struct ref_cache *refs = get_ref_cache(submodule); + struct ref_dir *loose_dir, *packed_dir; + struct ref_iterator *loose_iter, *packed_iter; + struct files_ref_iterator *iter; + struct ref_iterator *ref_iterator; + + if (!refs) + return empty_ref_iterator_begin(); if (ref_paranoia < 0) ref_paranoia = git_env_bool("GIT_REF_PARANOIA", 0); if (ref_paranoia) - data.flags |= DO_FOR_EACH_INCLUDE_BROKEN; + flags |= DO_FOR_EACH_INCLUDE_BROKEN; - return do_for_each_entry(refs, base, do_one_ref, &data); -} + iter = xcalloc(1, sizeof(*iter)); + ref_iterator = &iter->base; + base_ref_iterator_init(ref_iterator, &files_ref_iterator_vtable); -static void unlock_ref(struct ref_lock *lock) -{ - /* Do not free lock->lk -- atexit() still looks at them */ - if (lock->lk) - rollback_lock_file(lock->lk); - free(lock->ref_name); - free(lock->orig_ref_name); - free(lock); + /* + * 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 prime_ref_dir(), which pre-reads the loose + * references for the subtree 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 get_packed_ref_cache(), which + * internally checks whether the packed-ref cache is up to + * date with what is on disk, and re-reads it if not. + */ + + loose_dir = get_loose_refs(refs); + + if (prefix && *prefix) + loose_dir = find_containing_dir(loose_dir, prefix, 0); + + if (loose_dir) { + prime_ref_dir(loose_dir); + loose_iter = cache_ref_iterator_begin(loose_dir); + } else { + /* There's nothing to iterate over. */ + loose_iter = empty_ref_iterator_begin(); + } + + iter->packed_ref_cache = get_packed_ref_cache(refs); + acquire_packed_ref_cache(iter->packed_ref_cache); + packed_dir = get_packed_ref_dir(iter->packed_ref_cache); + + if (prefix && *prefix) + packed_dir = find_containing_dir(packed_dir, prefix, 0); + + if (packed_dir) { + packed_iter = cache_ref_iterator_begin(packed_dir); + } else { + /* There's nothing to iterate over. */ + packed_iter = empty_ref_iterator_begin(); + } + + iter->iter0 = overlay_ref_iterator_begin(loose_iter, packed_iter); + iter->flags = flags; + + return ref_iterator; } /* @@ -1721,18 +2038,18 @@ static int verify_lock(struct ref_lock *lock, lock->old_oid.hash, NULL)) { if (old_sha1) { int save_errno = errno; - strbuf_addf(err, "can't verify ref %s", lock->ref_name); + strbuf_addf(err, "can't verify ref '%s'", lock->ref_name); errno = save_errno; return -1; } else { - hashclr(lock->old_oid.hash); + oidclr(&lock->old_oid); return 0; } } if (old_sha1 && hashcmp(lock->old_oid.hash, old_sha1)) { - strbuf_addf(err, "ref %s is at %s but expected %s", + strbuf_addf(err, "ref '%s' is at %s but expected %s", lock->ref_name, - sha1_to_hex(lock->old_oid.hash), + oid_to_hex(&lock->old_oid), sha1_to_hex(old_sha1)); errno = EBUSY; return -1; @@ -1758,19 +2075,17 @@ static struct ref_lock *lock_ref_sha1_basic(const char *refname, const unsigned char *old_sha1, const struct string_list *extras, const struct string_list *skip, - unsigned int flags, int *type_p, + unsigned int flags, int *type, struct strbuf *err) { struct strbuf ref_file = STRBUF_INIT; - struct strbuf orig_ref_file = STRBUF_INIT; - const char *orig_refname = refname; struct ref_lock *lock; int last_errno = 0; - int type; - int lflags = 0; + int lflags = LOCK_NO_DEREF; int mustexist = (old_sha1 && !is_null_sha1(old_sha1)); - int resolve_flags = 0; + int resolve_flags = RESOLVE_REF_NO_RECURSE; int attempts_remaining = 3; + int resolved; assert(err); @@ -1780,48 +2095,39 @@ static struct ref_lock *lock_ref_sha1_basic(const char *refname, resolve_flags |= RESOLVE_REF_READING; if (flags & REF_DELETING) resolve_flags |= RESOLVE_REF_ALLOW_BAD_NAME; - if (flags & REF_NODEREF) { - resolve_flags |= RESOLVE_REF_NO_RECURSE; - lflags |= LOCK_NO_DEREF; - } - refname = resolve_ref_unsafe(refname, resolve_flags, - lock->old_oid.hash, &type); - if (!refname && errno == EISDIR) { + strbuf_git_path(&ref_file, "%s", refname); + resolved = !!resolve_ref_unsafe(refname, resolve_flags, + lock->old_oid.hash, type); + if (!resolved && errno == EISDIR) { /* * we are trying to lock foo but we used to * have foo/bar which now does not exist; * it is normal for the empty directory 'foo' * to remain. */ - strbuf_git_path(&orig_ref_file, "%s", orig_refname); - if (remove_empty_directories(&orig_ref_file)) { + if (remove_empty_directories(&ref_file)) { last_errno = errno; - if (!verify_refname_available_dir(orig_refname, extras, skip, + if (!verify_refname_available_dir(refname, extras, skip, get_loose_refs(&ref_cache), err)) strbuf_addf(err, "there are still refs under '%s'", - orig_refname); + refname); goto error_return; } - refname = resolve_ref_unsafe(orig_refname, resolve_flags, - lock->old_oid.hash, &type); + resolved = !!resolve_ref_unsafe(refname, resolve_flags, + lock->old_oid.hash, type); } - if (type_p) - *type_p = type; - if (!refname) { + if (!resolved) { last_errno = errno; if (last_errno != ENOTDIR || - !verify_refname_available_dir(orig_refname, extras, skip, + !verify_refname_available_dir(refname, extras, skip, get_loose_refs(&ref_cache), err)) - strbuf_addf(err, "unable to resolve reference %s: %s", - orig_refname, strerror(last_errno)); + strbuf_addf(err, "unable to resolve reference '%s': %s", + refname, strerror(last_errno)); goto error_return; } - if (flags & REF_NODEREF) - refname = orig_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 @@ -1838,8 +2144,6 @@ static struct ref_lock *lock_ref_sha1_basic(const char *refname, lock->lk = xcalloc(1, sizeof(struct lock_file)); lock->ref_name = xstrdup(refname); - lock->orig_ref_name = xstrdup(orig_refname); - strbuf_git_path(&ref_file, "%s", refname); retry: switch (safe_create_leading_directories_const(ref_file.buf)) { @@ -1851,7 +2155,7 @@ static struct ref_lock *lock_ref_sha1_basic(const char *refname, /* fall through */ default: last_errno = errno; - strbuf_addf(err, "unable to create directory for %s", + strbuf_addf(err, "unable to create directory for '%s'", ref_file.buf); goto error_return; } @@ -1882,7 +2186,6 @@ static struct ref_lock *lock_ref_sha1_basic(const char *refname, out: strbuf_release(&ref_file); - strbuf_release(&orig_ref_file); errno = last_errno; return lock; } @@ -2036,7 +2339,7 @@ static int pack_if_possible_fn(struct ref_entry *entry, void *cb_data) return 0; /* Do not pack symbolic or broken refs: */ - if ((entry->flag & REF_ISSYMREF) || !ref_resolves_to_object(entry)) + if ((entry->flag & REF_ISSYMREF) || !entry_resolves_to_object(entry)) return 0; /* Add a packed ref cache entry equivalent to the loose entry. */ @@ -2110,7 +2413,7 @@ static void prune_ref(struct ref_to_prune *r) transaction = ref_transaction_begin(&err); if (!transaction || ref_transaction_delete(transaction, r->name, r->sha1, - REF_ISPRUNING, NULL, &err) || + REF_ISPRUNING | REF_NODEREF, NULL, &err) || ref_transaction_commit(transaction, &err)) { ref_transaction_free(transaction); error("%s", err.buf); @@ -2222,7 +2525,7 @@ static int delete_ref_loose(struct ref_lock *lock, int flag, struct strbuf *err) return 0; } -int delete_refs(struct string_list *refnames) +int delete_refs(struct string_list *refnames, unsigned int flags) { struct strbuf err = STRBUF_INIT; int i, result = 0; @@ -2251,7 +2554,7 @@ int delete_refs(struct string_list *refnames) for (i = 0; i < refnames->nr; i++) { const char *refname = refnames->items[i].string; - if (delete_ref(refname, NULL, 0)) + if (delete_ref(refname, NULL, flags)) result |= error(_("could not remove reference %s"), refname); } @@ -2322,8 +2625,8 @@ out: } int verify_refname_available(const char *newname, - struct string_list *extras, - struct string_list *skip, + const struct string_list *extras, + const struct string_list *skip, struct strbuf *err) { struct ref_dir *packed_refs = get_packed_refs(&ref_cache); @@ -2342,7 +2645,7 @@ static int write_ref_to_lockfile(struct ref_lock *lock, const unsigned char *sha1, struct strbuf *err); static int commit_ref_update(struct ref_lock *lock, const unsigned char *sha1, const char *logmsg, - int flags, struct strbuf *err); + struct strbuf *err); int rename_ref(const char *oldrefname, const char *newrefname, const char *logmsg) { @@ -2351,20 +2654,18 @@ int rename_ref(const char *oldrefname, const char *newrefname, const char *logms struct ref_lock *lock; struct stat loginfo; int log = !lstat(git_path("logs/%s", oldrefname), &loginfo); - const char *symref = NULL; struct strbuf err = STRBUF_INIT; if (log && S_ISLNK(loginfo.st_mode)) return error("reflog for %s is a symlink", oldrefname); - symref = resolve_ref_unsafe(oldrefname, RESOLVE_REF_READING, - orig_sha1, &flag); + if (!resolve_ref_unsafe(oldrefname, RESOLVE_REF_READING | RESOLVE_REF_NO_RECURSE, + orig_sha1, &flag)) + return error("refname %s not found", oldrefname); + if (flag & REF_ISSYMREF) return error("refname %s is a symbolic ref, renaming it is not supported", oldrefname); - if (!symref) - return error("refname %s not found", oldrefname); - if (!rename_ref_available(oldrefname, newrefname)) return 1; @@ -2377,8 +2678,16 @@ int rename_ref(const char *oldrefname, const char *newrefname, const char *logms goto rollback; } - if (!read_ref_full(newrefname, RESOLVE_REF_READING, sha1, NULL) && - delete_ref(newrefname, sha1, REF_NODEREF)) { + /* + * Since we are doing a shallow lookup, sha1 is not the + * correct value to pass to delete_ref as old_sha1. But that + * doesn't matter, because an old_sha1 check wouldn't add to + * the safety anyway; we want to delete the reference whatever + * its current value. + */ + if (!read_ref_full(newrefname, RESOLVE_REF_READING | RESOLVE_REF_NO_RECURSE, + sha1, NULL) && + delete_ref(newrefname, NULL, REF_NODEREF)) { if (errno==EISDIR) { struct strbuf path = STRBUF_INIT; int result; @@ -2402,7 +2711,8 @@ int rename_ref(const char *oldrefname, const char *newrefname, const char *logms logmoved = log; - lock = lock_ref_sha1_basic(newrefname, NULL, NULL, NULL, 0, NULL, &err); + lock = lock_ref_sha1_basic(newrefname, NULL, NULL, NULL, REF_NODEREF, + NULL, &err); if (!lock) { error("unable to rename '%s' to '%s': %s", oldrefname, newrefname, err.buf); strbuf_release(&err); @@ -2411,7 +2721,7 @@ int rename_ref(const char *oldrefname, const char *newrefname, const char *logms hashcpy(lock->old_oid.hash, orig_sha1); if (write_ref_to_lockfile(lock, orig_sha1, &err) || - commit_ref_update(lock, orig_sha1, logmsg, 0, &err)) { + commit_ref_update(lock, orig_sha1, logmsg, &err)) { error("unable to write current sha1 into %s: %s", newrefname, err.buf); strbuf_release(&err); goto rollback; @@ -2420,7 +2730,8 @@ int rename_ref(const char *oldrefname, const char *newrefname, const char *logms return 0; rollback: - lock = lock_ref_sha1_basic(oldrefname, NULL, NULL, NULL, 0, NULL, &err); + lock = lock_ref_sha1_basic(oldrefname, NULL, NULL, NULL, REF_NODEREF, + NULL, &err); if (!lock) { error("unable to lock %s for rollback: %s", oldrefname, err.buf); strbuf_release(&err); @@ -2430,7 +2741,7 @@ int rename_ref(const char *oldrefname, const char *newrefname, const char *logms flag = log_all_ref_updates; log_all_ref_updates = 0; if (write_ref_to_lockfile(lock, orig_sha1, &err) || - commit_ref_update(lock, orig_sha1, NULL, 0, &err)) { + commit_ref_update(lock, orig_sha1, NULL, &err)) { error("unable to write current sha1 into %s: %s", oldrefname, err.buf); strbuf_release(&err); } @@ -2457,6 +2768,30 @@ static int close_ref(struct ref_lock *lock) 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; @@ -2475,7 +2810,7 @@ static int log_ref_setup(const char *refname, struct strbuf *logfile, struct str strbuf_git_path(logfile, "logs/%s", refname); if (force_create || should_autocreate_reflog(refname)) { if (safe_create_leading_directories(logfile->buf) < 0) { - strbuf_addf(err, "unable to create directory for %s: " + strbuf_addf(err, "unable to create directory for '%s': " "%s", logfile->buf, strerror(errno)); return -1; } @@ -2489,7 +2824,7 @@ static int log_ref_setup(const char *refname, struct strbuf *logfile, struct str if (errno == EISDIR) { if (remove_empty_directories(logfile)) { - strbuf_addf(err, "There are still logs under " + strbuf_addf(err, "there are still logs under " "'%s'", logfile->buf); return -1; } @@ -2497,7 +2832,7 @@ static int log_ref_setup(const char *refname, struct strbuf *logfile, struct str } if (logfd < 0) { - strbuf_addf(err, "unable to append to %s: %s", + strbuf_addf(err, "unable to append to '%s': %s", logfile->buf, strerror(errno)); return -1; } @@ -2566,13 +2901,13 @@ static int log_ref_write_1(const char *refname, const unsigned char *old_sha1, result = log_ref_write_fd(logfd, old_sha1, new_sha1, git_committer_info(0), msg); if (result) { - strbuf_addf(err, "unable to append to %s: %s", logfile->buf, + strbuf_addf(err, "unable to append to '%s': %s", logfile->buf, strerror(errno)); close(logfd); return -1; } if (close(logfd)) { - strbuf_addf(err, "unable to append to %s: %s", logfile->buf, + strbuf_addf(err, "unable to append to '%s': %s", logfile->buf, strerror(errno)); return -1; } @@ -2613,14 +2948,14 @@ static int write_ref_to_lockfile(struct ref_lock *lock, o = parse_object(sha1); if (!o) { strbuf_addf(err, - "Trying to write ref %s with nonexistent object %s", + "trying to write ref '%s' with nonexistent object %s", lock->ref_name, sha1_to_hex(sha1)); 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", + "trying to write non-commit object %s to branch '%s'", sha1_to_hex(sha1), lock->ref_name); unlock_ref(lock); return -1; @@ -2630,7 +2965,7 @@ static int write_ref_to_lockfile(struct ref_lock *lock, write_in_full(fd, &term, 1) != 1 || close_ref(lock) < 0) { strbuf_addf(err, - "Couldn't write %s", get_lock_file_path(lock->lk)); + "couldn't write '%s'", get_lock_file_path(lock->lk)); unlock_ref(lock); return -1; } @@ -2644,20 +2979,19 @@ static int write_ref_to_lockfile(struct ref_lock *lock, */ static int commit_ref_update(struct ref_lock *lock, const unsigned char *sha1, const char *logmsg, - int flags, struct strbuf *err) + struct strbuf *err) { clear_loose_ref_cache(&ref_cache); - if (log_ref_write(lock->ref_name, lock->old_oid.hash, sha1, logmsg, flags, err) < 0 || - (strcmp(lock->ref_name, lock->orig_ref_name) && - log_ref_write(lock->orig_ref_name, lock->old_oid.hash, sha1, logmsg, flags, err) < 0)) { + if (log_ref_write(lock->ref_name, lock->old_oid.hash, sha1, logmsg, 0, err)) { char *old_msg = strbuf_detach(err, NULL); - strbuf_addf(err, "Cannot update the ref '%s': %s", + 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->orig_ref_name, "HEAD") != 0) { + + 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 @@ -2673,6 +3007,7 @@ static int commit_ref_update(struct ref_lock *lock, unsigned char head_sha1[20]; int head_flag; const char *head_ref; + head_ref = resolve_ref_unsafe("HEAD", RESOLVE_REF_READING, head_sha1, &head_flag); if (head_ref && (head_flag & REF_ISSYMREF) && @@ -2685,8 +3020,9 @@ static int commit_ref_update(struct ref_lock *lock, } } } + if (commit_ref(lock)) { - error("Couldn't set %s", lock->ref_name); + strbuf_addf(err, "couldn't set '%s'", lock->ref_name); unlock_ref(lock); return -1; } @@ -2790,7 +3126,6 @@ int set_worktree_head_symref(const char *gitdir, const char *target) lock = xcalloc(1, sizeof(struct ref_lock)); lock->lk = &head_lock; lock->ref_name = xstrdup(head_rel); - lock->orig_ref_name = xstrdup(head_rel); ret = create_symref_locked(lock, head_rel, target, NULL); @@ -2969,60 +3304,88 @@ int for_each_reflog_ent(const char *refname, each_reflog_ent_fn fn, void *cb_dat strbuf_release(&sb); return ret; } -/* - * Call fn for each reflog in the namespace indicated by name. name - * must be empty or end with '/'. Name will be used as a scratch - * space, but its contents will be restored before return. - */ -static int do_for_each_reflog(struct strbuf *name, each_ref_fn fn, void *cb_data) -{ - DIR *d = opendir(git_path("logs/%s", name->buf)); - int retval = 0; - struct dirent *de; - int oldlen = name->len; - if (!d) - return name->len ? errno : 0; +struct files_reflog_iterator { + struct ref_iterator base; - while ((de = readdir(d)) != NULL) { - struct stat st; + struct dir_iterator *dir_iterator; + struct object_id oid; +}; - if (de->d_name[0] == '.') +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 (ends_with(de->d_name, ".lock")) + if (diter->basename[0] == '.') + continue; + if (ends_with(diter->basename, ".lock")) continue; - strbuf_addstr(name, de->d_name); - if (stat(git_path("logs/%s", name->buf), &st) < 0) { - ; /* silently ignore */ - } else { - if (S_ISDIR(st.st_mode)) { - strbuf_addch(name, '/'); - retval = do_for_each_reflog(name, fn, cb_data); - } else { - struct object_id oid; - if (read_ref_full(name->buf, 0, oid.hash, NULL)) - retval = error("bad ref for %s", name->buf); - else - retval = fn(name->buf, &oid, 0, cb_data); - } - if (retval) - break; + if (read_ref_full(diter->relative_path, 0, + iter->oid.hash, &flags)) { + error("bad ref for %s", diter->path.buf); + continue; } - strbuf_setlen(name, oldlen); + + iter->base.refname = diter->relative_path; + iter->base.oid = &iter->oid; + iter->base.flags = flags; + return ITER_OK; } - closedir(d); - return retval; + + 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, + struct object_id *peeled) +{ + die("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 = { + files_reflog_iterator_advance, + files_reflog_iterator_peel, + files_reflog_iterator_abort +}; + +struct ref_iterator *files_reflog_iterator_begin(void) +{ + struct files_reflog_iterator *iter = xcalloc(1, sizeof(*iter)); + struct ref_iterator *ref_iterator = &iter->base; + + base_ref_iterator_init(ref_iterator, &files_reflog_iterator_vtable); + iter->dir_iterator = dir_iterator_begin(git_path("logs")); + return ref_iterator; } int for_each_reflog(each_ref_fn fn, void *cb_data) { - int retval; - struct strbuf name; - strbuf_init(&name, PATH_MAX); - retval = do_for_each_reflog(&name, fn, cb_data); - strbuf_release(&name); - return retval; + return do_for_each_ref_iterator(files_reflog_iterator_begin(), + fn, cb_data); } static int ref_update_reject_duplicates(struct string_list *refnames, @@ -3035,36 +3398,352 @@ static int ref_update_reject_duplicates(struct string_list *refnames, for (i = 1; i < n; i++) if (!strcmp(refnames->items[i - 1].string, refnames->items[i].string)) { strbuf_addf(err, - "Multiple updates for ref '%s' not allowed.", + "multiple updates for ref '%s' not allowed.", refnames->items[i].string); return 1; } return 0; } +/* + * 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_ISPRUNING) || + (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 insertion is O(N) in the transaction + * size, but it happens at most once per transaction. + */ + item = string_list_insert(affected_refnames, "HEAD"); + if (item->util) { + /* 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_NODEREF, + update->new_sha1, update->old_sha1, + update->msg); + + item->util = new_update; + + return 0; +} + +/* + * update is for a symref that points at referent and doesn't have + * REF_NODEREF set. Split it into two updates: + * - The original update, but with REF_LOG_ONLY and REF_NODEREF 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 insertion is O(N) in the transaction + * size, but it happens at most once per symref in a + * transaction. + */ + item = string_list_insert(affected_refnames, referent); + if (item->util) { + /* An entry already existed */ + 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_sha1, update->old_sha1, + update->msg); + + new_update->parent_update = update; + + /* + * Change the symbolic ref update to log only. Also, it + * doesn't need to check its old SHA-1 value, as that will be + * done when new_update is processed. + */ + update->flags |= REF_LOG_ONLY | REF_NODEREF; + update->flags &= ~REF_HAVE_OLD; + + 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) || + !hashcmp(oid->hash, update->old_sha1)) + return 0; + + if (is_null_sha1(update->old_sha1)) + 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), + sha1_to_hex(update->old_sha1)); + else + strbuf_addf(err, "cannot lock ref '%s': " + "is at %s but expected %s", + original_update_refname(update), + oid_to_hex(oid), + sha1_to_hex(update->old_sha1)); + + return -1; +} + +/* + * Prepare for carrying out update: + * - Lock the reference referred to by update. + * - Read the reference under lock. + * - Check that its old SHA-1 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_NODEREF, 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 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_sha1(update->old_sha1); + int ret; + struct ref_lock *lock; + + if ((update->flags & REF_HAVE_NEW) && is_null_sha1(update->new_sha1)) + update->flags |= REF_DELETING; + + if (head_ref) { + ret = split_head_update(update, transaction, head_ref, + affected_refnames, err); + if (ret) + return ret; + } + + ret = lock_raw_ref(update->refname, mustexist, + affected_refnames, NULL, + &update->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); + return ret; + } + + lock = update->lock; + + if (update->type & REF_ISSYMREF) { + if (update->flags & REF_NODEREF) { + /* + * 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_sha1: + */ + if (read_ref_full(referent.buf, 0, + lock->old_oid.hash, NULL)) { + if (update->flags & REF_HAVE_OLD) { + strbuf_addf(err, "cannot lock ref '%s': " + "error reading reference", + original_update_refname(update)); + return -1; + } + } else if (check_old_oid(update, &lock->old_oid, err)) { + return TRANSACTION_GENERIC_ERROR; + } + } else { + /* + * Create a new update for the reference this + * symref is pointing at. Also, we will record + * and verify old_sha1 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) + return ret; + } + } else { + struct ref_update *parent_update; + + if (check_old_oid(update, &lock->old_oid, err)) + return TRANSACTION_GENERIC_ERROR; + + /* + * If this update is happening indirectly because of a + * symref update, record the old SHA-1 in the parent + * update: + */ + for (parent_update = update->parent_update; + parent_update; + parent_update = parent_update->parent_update) { + oidcpy(&parent_update->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) && + !hashcmp(lock->old_oid.hash, update->new_sha1)) { + /* + * The reference already has the desired + * value, so we don't need to write it. + */ + } else if (write_ref_to_lockfile(lock, update->new_sha1, + err)) { + char *write_err = strbuf_detach(err, NULL); + + /* + * The lock was freed upon failure of + * write_ref_to_lockfile(): + */ + update->lock = NULL; + strbuf_addf(err, + "cannot update ref '%s': %s", + update->refname, write_err); + free(write_err); + return TRANSACTION_GENERIC_ERROR; + } 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(lock)) { + strbuf_addf(err, "couldn't close '%s.lock'", + update->refname); + return TRANSACTION_GENERIC_ERROR; + } + } + return 0; +} + int ref_transaction_commit(struct ref_transaction *transaction, struct strbuf *err) { int ret = 0, i; - int n = transaction->nr; - struct ref_update **updates = transaction->updates; struct string_list refs_to_delete = STRING_LIST_INIT_NODUP; struct string_list_item *ref_to_delete; struct string_list affected_refnames = STRING_LIST_INIT_NODUP; + char *head_ref = NULL; + int head_type; + struct object_id head_oid; assert(err); if (transaction->state != REF_TRANSACTION_OPEN) die("BUG: commit called for transaction that is not open"); - if (!n) { + if (!transaction->nr) { transaction->state = REF_TRANSACTION_CLOSED; return 0; } - /* Fail if a refname appears more than once in the transaction: */ - for (i = 0; i < n; i++) - string_list_append(&affected_refnames, updates[i]->refname); + /* + * 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.) + */ + 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); + + /* + * 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; @@ -3072,105 +3751,84 @@ int ref_transaction_commit(struct ref_transaction *transaction, } /* + * 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 = resolve_refdup("HEAD", RESOLVE_REF_NO_RECURSE, + head_oid.hash, &head_type); + + if (head_ref && !(head_type & REF_ISSYMREF)) { + free(head_ref); + head_ref = NULL; + } + + /* * 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. */ - for (i = 0; i < n; i++) { - struct ref_update *update = updates[i]; + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; - if ((update->flags & REF_HAVE_NEW) && - is_null_sha1(update->new_sha1)) - update->flags |= REF_DELETING; - update->lock = lock_ref_sha1_basic( - update->refname, - ((update->flags & REF_HAVE_OLD) ? - update->old_sha1 : NULL), - &affected_refnames, NULL, - update->flags, - &update->type, - err); - if (!update->lock) { - char *reason; - - ret = (errno == ENOTDIR) - ? TRANSACTION_NAME_CONFLICT - : TRANSACTION_GENERIC_ERROR; - reason = strbuf_detach(err, NULL); - strbuf_addf(err, "cannot lock ref '%s': %s", - update->refname, reason); - free(reason); + ret = lock_ref_for_update(update, transaction, head_ref, + &affected_refnames, err); + if (ret) goto cleanup; - } - if ((update->flags & REF_HAVE_NEW) && - !(update->flags & REF_DELETING)) { - int overwriting_symref = ((update->type & REF_ISSYMREF) && - (update->flags & REF_NODEREF)); - - if (!overwriting_symref && - !hashcmp(update->lock->old_oid.hash, update->new_sha1)) { - /* - * The reference already has the desired - * value, so we don't need to write it. - */ - } else if (write_ref_to_lockfile(update->lock, - update->new_sha1, - err)) { - char *write_err = strbuf_detach(err, NULL); + } - /* - * The lock was freed upon failure of - * write_ref_to_lockfile(): - */ + /* 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->lock; + + if (update->flags & REF_NEEDS_COMMIT || + update->flags & REF_LOG_ONLY) { + if (log_ref_write(lock->ref_name, lock->old_oid.hash, + update->new_sha1, + 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->lock = NULL; - strbuf_addf(err, - "cannot update the ref '%s': %s", - update->refname, write_err); - free(write_err); ret = TRANSACTION_GENERIC_ERROR; goto cleanup; - } else { - update->flags |= REF_NEEDS_COMMIT; - } - } - if (!(update->flags & REF_NEEDS_COMMIT)) { - /* - * We didn't have to write anything to the lockfile. - * Close it to free up the file descriptor: - */ - if (close_ref(update->lock)) { - strbuf_addf(err, "Couldn't close %s.lock", - update->refname); - goto cleanup; } } - } - - /* Perform updates first so live commits remain referenced */ - for (i = 0; i < n; i++) { - struct ref_update *update = updates[i]; - if (update->flags & REF_NEEDS_COMMIT) { - if (commit_ref_update(update->lock, - update->new_sha1, update->msg, - update->flags, err)) { - /* freed by commit_ref_update(): */ + clear_loose_ref_cache(&ref_cache); + if (commit_ref(lock)) { + strbuf_addf(err, "couldn't set '%s'", lock->ref_name); + unlock_ref(lock); update->lock = NULL; ret = TRANSACTION_GENERIC_ERROR; goto cleanup; - } else { - /* freed by commit_ref_update(): */ - update->lock = NULL; } } } - /* Perform deletes now that updates are safely completed */ - for (i = 0; i < n; i++) { - struct ref_update *update = updates[i]; + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; - if (update->flags & REF_DELETING) { + if (update->flags & REF_DELETING && + !(update->flags & REF_LOG_ONLY)) { if (delete_ref_loose(update->lock, update->type, err)) { ret = TRANSACTION_GENERIC_ERROR; goto cleanup; @@ -3193,11 +3851,13 @@ int ref_transaction_commit(struct ref_transaction *transaction, cleanup: transaction->state = REF_TRANSACTION_CLOSED; - for (i = 0; i < n; i++) - if (updates[i]->lock) - unlock_ref(updates[i]->lock); + for (i = 0; i < transaction->nr; i++) + if (transaction->updates[i]->lock) + unlock_ref(transaction->updates[i]->lock); string_list_clear(&refs_to_delete, 0); + free(head_ref); string_list_clear(&affected_refnames, 0); + return ret; } @@ -3213,8 +3873,6 @@ int initial_ref_transaction_commit(struct ref_transaction *transaction, struct strbuf *err) { int ret = 0, i; - int n = transaction->nr; - struct ref_update **updates = transaction->updates; struct string_list affected_refnames = STRING_LIST_INIT_NODUP; assert(err); @@ -3223,8 +3881,9 @@ int initial_ref_transaction_commit(struct ref_transaction *transaction, die("BUG: commit called for transaction that is not open"); /* Fail if a refname appears more than once in the transaction: */ - for (i = 0; i < n; i++) - string_list_append(&affected_refnames, updates[i]->refname); + 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; @@ -3246,8 +3905,8 @@ int initial_ref_transaction_commit(struct ref_transaction *transaction, if (for_each_rawref(ref_present, &affected_refnames)) die("BUG: initial ref transaction called with existing refs"); - for (i = 0; i < n; i++) { - struct ref_update *update = updates[i]; + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; if ((update->flags & REF_HAVE_OLD) && !is_null_sha1(update->old_sha1)) @@ -3267,8 +3926,8 @@ int initial_ref_transaction_commit(struct ref_transaction *transaction, goto cleanup; } - for (i = 0; i < n; i++) { - struct ref_update *update = updates[i]; + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; if ((update->flags & REF_HAVE_NEW) && !is_null_sha1(update->new_sha1)) diff --git a/refs/iterator.c b/refs/iterator.c new file mode 100644 index 0000000000..bce1f192f7 --- /dev/null +++ b/refs/iterator.c @@ -0,0 +1,384 @@ +/* + * 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) +{ + iter->vtable = vtable; + 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, + struct object_id *peeled) +{ + die("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 = { + empty_ref_iterator_advance, + empty_ref_iterator_peel, + 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); + 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) { + die("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 = { + merge_ref_iterator_advance, + merge_ref_iterator_peel, + merge_ref_iterator_abort +}; + +struct ref_iterator *merge_ref_iterator_begin( + 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); + 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) +{ + 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; + } + + return merge_ref_iterator_begin(front, back, + overlay_iterator_select, NULL); +} + +struct prefix_ref_iterator { + struct ref_iterator base; + + struct ref_iterator *iter0; + char *prefix; + int trim; +}; + +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) { + if (!starts_with(iter->iter0->refname, iter->prefix)) + continue; + + iter->base.refname = iter->iter0->refname + iter->trim; + 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 = { + prefix_ref_iterator_advance, + prefix_ref_iterator_peel, + 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 */ + + iter = xcalloc(1, sizeof(*iter)); + ref_iterator = &iter->base; + + base_ref_iterator_init(ref_iterator, &prefix_ref_iterator_vtable); + + iter->iter0 = iter0; + iter->prefix = xstrdup(prefix); + iter->trim = trim; + + return ref_iterator; +} + +struct ref_iterator *current_ref_iter = NULL; + +int do_for_each_ref_iterator(struct ref_iterator *iter, + each_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(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/refs-internal.h b/refs/refs-internal.h index 3a4f634cb4..efe584701b 100644 --- a/refs/refs-internal.h +++ b/refs/refs-internal.h @@ -15,7 +15,7 @@ /* * Used as a flag in ref_update::flags when a loose ref is being - * pruned. + * pruned. This flag must only be used when REF_NODEREF is set. */ #define REF_ISPRUNING 0x04 @@ -43,6 +43,19 @@ */ /* + * 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 0x80 + +/* + * Internal flag, meaning that the containing ref_update was via an + * update to HEAD. + */ +#define REF_UPDATE_VIA_HEAD 0x100 + +/* * 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. @@ -109,8 +122,8 @@ enum peel_status peel_object(const unsigned char *name, unsigned char *sha1); * extras and skip must be sorted. */ int verify_refname_available(const char *newname, - struct string_list *extras, - struct string_list *skip, + const struct string_list *extras, + const struct string_list *skip, struct strbuf *err); /* @@ -130,27 +143,59 @@ int should_autocreate_reflog(const char *refname); * not exist before update. */ struct ref_update { + /* * If (flags & REF_HAVE_NEW), set the reference to this value: */ unsigned char new_sha1[20]; + /* * If (flags & REF_HAVE_OLD), check that the reference * previously had this value: */ unsigned char old_sha1[20]; + /* * One or more of REF_HAVE_NEW, REF_HAVE_OLD, REF_NODEREF, - * REF_DELETING, and REF_ISPRUNING: + * REF_DELETING, REF_ISPRUNING, REF_LOG_ONLY, and + * REF_UPDATE_VIA_HEAD: */ unsigned int flags; + struct ref_lock *lock; - int type; + 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]; }; /* + * 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_sha1 and old_sha1 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 unsigned char *new_sha1, + const unsigned char *old_sha1, + const char *msg); + +/* * Transaction states. * OPEN: The transaction is in a valid state and can accept new updates. * An OPEN transaction can be committed. @@ -204,12 +249,270 @@ int rename_ref_available(const char *oldname, const char *newname); #define DO_FOR_EACH_INCLUDE_BROKEN 0x01 /* - * The common backend for the for_each_*ref* functions + * 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 + * assocated 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; + 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); + +/* + * 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. */ -int do_for_each_ref(const char *submodule, const char *base, - each_ref_fn fn, int trim, int flags, void *cb_data); +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. + */ +struct ref_iterator *merge_ref_iterator_begin( + 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. + */ +struct ref_iterator *prefix_ref_iterator_begin(struct ref_iterator *iter0, + const char *prefix, + int trim); + +/* + * Iterate over the packed and loose references in the specified + * submodule that are within find_containing_dir(prefix). If prefix is + * NULL or the empty string, iterate over all references in the + * submodule. + */ +struct ref_iterator *files_ref_iterator_begin(const char *submodule, + const char *prefix, + unsigned int flags); + +/* + * Iterate over the references in the main ref_store that have a + * reflog. The paths within a directory are iterated over in arbitrary + * order. + */ +struct ref_iterator *files_reflog_iterator_begin(void); + +/* Internal implementation of reference iteration: */ + +/* + * Base class constructor for ref_iterators. Initialize the + * ref_iterator part of iter, setting its vtable pointer as specified. + * 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); + +/* + * 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: */ + +typedef int ref_iterator_advance_fn(struct ref_iterator *ref_iterator); + +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_ref_iterator(struct ref_iterator *iter, + each_ref_fn fn, void *cb_data); + +/* + * Read the specified reference from the filesystem or packed refs + * file, non-recursively. Set type to describe the reference, and: + * + * - If refname is the name of a normal reference, fill in sha1 + * (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 sha1 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. If the ref doesn't exist, set errno to ENOENT + * and return -1. If the ref exists but is neither a symbolic ref nor + * a sha1, it is broken; set REF_ISBROKEN in type, set errno to + * EINVAL, and return -1. If there is another error reading the ref, + * set errno appropriately and return -1. + * + * 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. + */ int read_raw_ref(const char *refname, unsigned char *sha1, - struct strbuf *symref, unsigned int *flags); + struct strbuf *referent, unsigned int *type); #endif /* REFS_REFS_INTERNAL_H */ |