diff options
Diffstat (limited to 'refs/files-backend.c')
| -rw-r--r-- | refs/files-backend.c | 4142 |
1 files changed, 4142 insertions, 0 deletions
diff --git a/refs/files-backend.c b/refs/files-backend.c new file mode 100644 index 0000000000..50188e92f9 --- /dev/null +++ b/refs/files-backend.c @@ -0,0 +1,4142 @@ +#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; + struct lock_file *lk; + struct object_id old_oid; +}; + +struct ref_entry; + +/* + * 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; + + /* + * If REF_KNOWS_PEELED, then this field holds the peeled value + * of this reference, or null if the reference is known not to + * be peelable. See the documentation for peel_ref() for an + * exact definition of "peelable". + */ + struct object_id peeled; +}; + +struct files_ref_store; + +/* + * 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; + + /* A pointer to the files_ref_store that contains this ref_dir. */ + struct files_ref_store *ref_store; + + 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. + */ + +/* + * The field ref_entry->u.value.peeled of this value entry contains + * the correct peeled value for the reference, which might be + * null_sha1 if the reference is not a tag or if it is broken. + */ +#define REF_KNOWS_PEELED 0x10 + +/* ref_entry represents a directory of references */ +#define REF_DIR 0x20 + +/* + * Entry has not yet been read from disk (used only for REF_DIR + * entries representing loose references) + */ +#define REF_INCOMPLETE 0x40 + +/* + * 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 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]; +}; + +static void read_loose_refs(const char *dirname, struct ref_dir *dir); +static int search_ref_dir(struct ref_dir *dir, const char *refname, size_t len); +static struct ref_entry *create_dir_entry(struct files_ref_store *ref_store, + const char *dirname, size_t len, + int incomplete); +static void add_entry_to_dir(struct ref_dir *dir, struct ref_entry *entry); + +static 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) { + read_loose_refs(entry->name, dir); + + /* + * Manually add refs/bisect, which, being + * per-worktree, might not appear in the directory + * listing for refs/ in the main repo. + */ + if (!strcmp(entry->name, "refs/")) { + int pos = search_ref_dir(dir, "refs/bisect/", 12); + if (pos < 0) { + struct ref_entry *child_entry; + child_entry = create_dir_entry(dir->ref_store, + "refs/bisect/", + 12, 1); + add_entry_to_dir(dir, child_entry); + read_loose_refs("refs/bisect", + &child_entry->u.subdir); + } + } + entry->flag &= ~REF_INCOMPLETE; + } + return dir; +} + +static struct ref_entry *create_ref_entry(const char *refname, + const unsigned char *sha1, int flag, + int check_name) +{ + struct ref_entry *ref; + + if (check_name && + check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) + die("Reference has invalid format: '%s'", refname); + FLEX_ALLOC_STR(ref, name, refname); + hashcpy(ref->u.value.oid.hash, sha1); + oidclr(&ref->u.value.peeled); + ref->flag = flag; + return ref; +} + +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); +} + +/* + * Add a ref_entry to the end of dir (unsorted). Entry is always + * stored directly in dir; no recursion into subdirectories is + * done. + */ +static 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; +} + +/* + * 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(dir->entries); + dir->sorted = dir->nr = dir->alloc = 0; + dir->entries = NULL; +} + +/* + * 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. + */ +static struct ref_entry *create_dir_entry(struct files_ref_store *ref_store, + const char *dirname, size_t len, + int incomplete) +{ + struct ref_entry *direntry; + FLEX_ALLOC_MEM(direntry, name, dirname, len); + direntry->u.subdir.ref_store = ref_store; + direntry->flag = REF_DIR | (incomplete ? REF_INCOMPLETE : 0); + 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]; +} + +/* + * 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. + */ +static 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 == NULL) + 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 '/'). If mkdir is set, then create the + * directory if it is missing; otherwise, return 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 mkdir) +{ + int entry_index = search_ref_dir(dir, subdirname, len); + struct ref_entry *entry; + if (entry_index == -1) { + if (!mkdir) + return NULL; + /* + * Since dir is complete, the absence of a subdir + * means that the subdir really doesn't exist; + * therefore, create an empty record for it but mark + * the record complete. + */ + entry = create_dir_entry(dir->ref_store, subdirname, len, 0); + add_entry_to_dir(dir, entry); + } else { + 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., 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. If + * mkdir is set, then create any missing directories; otherwise, + * return NULL if the desired directory cannot be found. + */ +static struct ref_dir *find_containing_dir(struct ref_dir *dir, + const char *refname, int mkdir) +{ + 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, mkdir); + if (!subdir) { + dir = NULL; + break; + } + dir = subdir; + } + + return dir; +} + +/* + * 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. + */ +static struct ref_entry *find_ref(struct ref_dir *dir, const char *refname) +{ + int entry_index; + struct ref_entry *entry; + dir = find_containing_dir(dir, refname, 0); + 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; +} + +/* + * Remove the entry with the given name from dir, recursing into + * subdirectories as necessary. If refname is the name of a directory + * (i.e., ends with '/'), then remove the directory and its contents. + * If the removal was successful, return the number of entries + * remaining in the directory entry that contained the deleted entry. + * If the name was not found, return -1. Please note that this + * function only deletes the entry from the cache; it does not delete + * it from the filesystem or ensure that other cache entries (which + * might be symbolic references to the removed entry) are updated. + * Nor does it remove any containing dir entries that might be made + * empty by the removal. dir must represent the top-level directory + * and must already be complete. + */ +static int remove_entry(struct ref_dir *dir, const char *refname) +{ + int refname_len = strlen(refname); + int entry_index; + struct ref_entry *entry; + int is_dir = refname[refname_len - 1] == '/'; + if (is_dir) { + /* + * refname represents a reference directory. Remove + * the trailing slash; otherwise we will get the + * directory *representing* refname rather than the + * one *containing* it. + */ + char *dirname = xmemdupz(refname, refname_len - 1); + dir = find_containing_dir(dir, dirname, 0); + free(dirname); + } else { + dir = find_containing_dir(dir, refname, 0); + } + if (!dir) + return -1; + entry_index = search_ref_dir(dir, refname, refname_len); + if (entry_index == -1) + return -1; + entry = dir->entries[entry_index]; + + memmove(&dir->entries[entry_index], + &dir->entries[entry_index + 1], + (dir->nr - entry_index - 1) * sizeof(*dir->entries) + ); + dir->nr--; + if (dir->sorted > entry_index) + dir->sorted--; + free_ref_entry(entry); + return dir->nr; +} + +/* + * Add a ref_entry to the ref_dir (unsorted), recursing into + * subdirectories as necessary. dir must represent the top-level + * directory. Return 0 on success. + */ +static int add_ref(struct ref_dir *dir, struct ref_entry *ref) +{ + dir = find_containing_dir(dir, ref->name, 1); + if (!dir) + return -1; + add_entry_to_dir(dir, ref); + return 0; +} + +/* + * Emit a warning and return true iff ref1 and ref2 have the same name + * and the same sha1. Die if they have the same name but different + * sha1s. + */ +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 (oidcmp(&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; +} + +/* + * 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(const char *refname, + const struct object_id *oid, + unsigned int flags) +{ + if (flags & REF_ISBROKEN) + return 0; + if (!has_sha1_file(oid->hash)) { + error("%s does not point to a valid object!", refname); + return 0; + } + return 1; +} + +/* + * 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 entry_resolves_to_object(struct ref_entry *entry) +{ + 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 + * that index range, sorting them before iterating. This function + * does not sort dir itself; it should be sorted beforehand. fn is + * called for all references, including broken ones. + */ +static int do_for_each_entry_in_dir(struct ref_dir *dir, int offset, + each_ref_entry_fn fn, void *cb_data) +{ + int i; + assert(dir->sorted == dir->nr); + for (i = offset; i < dir->nr; i++) { + struct ref_entry *entry = dir->entries[i]; + int retval; + if (entry->flag & REF_DIR) { + struct ref_dir *subdir = get_ref_dir(entry); + sort_ref_dir(subdir); + retval = do_for_each_entry_in_dir(subdir, 0, fn, cb_data); + } else { + retval = fn(entry, cb_data); + } + if (retval) + return retval; + } + return 0; +} + +/* + * 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 + * sorting, as traversal order does not matter to us. + */ +static void prime_ref_dir(struct ref_dir *dir) +{ + int i; + for (i = 0; i < dir->nr; i++) { + struct ref_entry *entry = dir->entries[i]; + if (entry->flag & REF_DIR) + prime_ref_dir(get_ref_dir(entry)); + } +} + +/* + * 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; + oidcpy(peeled, &entry->u.value.peeled); + 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; +}; + +static int nonmatching_ref_fn(struct ref_entry *entry, void *vdata) +{ + struct nonmatching_ref_data *data = vdata; + + if (data->skip && string_list_has_string(data->skip, entry->name)) + return 0; + + data->conflicting_refname = entry->name; + return 1; +} + +/* + * Return 0 if a reference named refname could be created without + * conflicting with the name of an existing reference in dir. + * See verify_refname_available for more information. + */ +static int verify_refname_available_dir(const char *refname, + const struct string_list *extras, + const struct string_list *skip, + struct ref_dir *dir, + struct strbuf *err) +{ + const char *slash; + const char *extra_refname; + int pos; + struct strbuf dirname = STRBUF_INIT; + int ret = -1; + + /* + * For the sake of comments in this function, suppose that + * refname is "refs/foo/bar". + */ + + assert(err); + + strbuf_grow(&dirname, strlen(refname) + 1); + for (slash = strchr(refname, '/'); slash; slash = strchr(slash + 1, '/')) { + /* Expand dirname to the new prefix, not including the trailing slash: */ + strbuf_add(&dirname, refname + dirname.len, slash - refname - dirname.len); + + /* + * We are still at a leading dir of the refname (e.g., + * "refs/foo"; if there is a reference with that name, + * it is a conflict, *unless* it is in skip. + */ + if (dir) { + pos = search_ref_dir(dir, dirname.buf, dirname.len); + if (pos >= 0 && + (!skip || !string_list_has_string(skip, dirname.buf))) { + /* + * We found a reference whose name is + * a proper prefix of refname; e.g., + * "refs/foo", and is not in skip. + */ + strbuf_addf(err, "'%s' exists; cannot create '%s'", + dirname.buf, refname); + goto cleanup; + } + } + + if (extras && string_list_has_string(extras, dirname.buf) && + (!skip || !string_list_has_string(skip, dirname.buf))) { + strbuf_addf(err, "cannot process '%s' and '%s' at the same time", + refname, dirname.buf); + goto cleanup; + } + + /* + * Otherwise, we can try to continue our search with + * the next component. So try to look up the + * directory, e.g., "refs/foo/". If we come up empty, + * we know there is nothing under this whole prefix, + * but even in that case we still have to continue the + * search for conflicts with extras. + */ + strbuf_addch(&dirname, '/'); + if (dir) { + pos = search_ref_dir(dir, dirname.buf, dirname.len); + if (pos < 0) { + /* + * There was no directory "refs/foo/", + * so there is nothing under this + * whole prefix. So there is no need + * to continue looking for conflicting + * references. But we need to continue + * looking for conflicting extras. + */ + dir = NULL; + } else { + dir = get_ref_dir(dir->entries[pos]); + } + } + } + + /* + * We are at the leaf of our refname (e.g., "refs/foo/bar"). + * There is no point in searching for a reference with that + * name, because a refname isn't considered to conflict with + * itself. But we still need to check for references whose + * names are in the "refs/foo/bar/" namespace, because they + * *do* conflict. + */ + strbuf_addstr(&dirname, refname + dirname.len); + strbuf_addch(&dirname, '/'); + + if (dir) { + pos = search_ref_dir(dir, dirname.buf, dirname.len); + + if (pos >= 0) { + /* + * We found a directory named "$refname/" + * (e.g., "refs/foo/bar/"). It is a problem + * iff it contains any ref that is not in + * "skip". + */ + struct nonmatching_ref_data data; + + data.skip = skip; + data.conflicting_refname = NULL; + dir = get_ref_dir(dir->entries[pos]); + sort_ref_dir(dir); + if (do_for_each_entry_in_dir(dir, 0, nonmatching_ref_fn, &data)) { + strbuf_addf(err, "'%s' exists; cannot create '%s'", + data.conflicting_refname, refname); + goto cleanup; + } + } + } + + extra_refname = find_descendant_ref(dirname.buf, extras, skip); + if (extra_refname) + strbuf_addf(err, "cannot process '%s' and '%s' at the same time", + refname, extra_refname); + else + ret = 0; + +cleanup: + strbuf_release(&dirname); + return ret; +} + +struct packed_ref_cache { + struct ref_entry *root; + + /* + * Count of references to the data structure in this instance, + * including the pointer from files_ref_store::packed if any. + * The data will not be freed as long as the reference count + * is nonzero. + */ + unsigned int referrers; + + /* + * Iff the packed-refs file associated with this instance is + * currently locked for writing, this points at the associated + * lock (which is owned by somebody else). The referrer count + * is also incremented when the file is locked and decremented + * when it is unlocked. + */ + struct lock_file *lock; + + /* The metadata from when this packed-refs cache was read */ + struct stat_validity validity; +}; + +/* + * Future: need to be in "struct repository" + * when doing a full libification. + */ +struct files_ref_store { + struct ref_store base; + + /* + * The name of the submodule represented by this object, or + * NULL if it represents the main repository's reference + * store: + */ + const char *submodule; + + struct ref_entry *loose; + struct packed_ref_cache *packed; +}; + +/* Lock used for the main packed-refs file: */ +static struct lock_file packlock; + +/* + * Increment the reference count of *packed_refs. + */ +static void acquire_packed_ref_cache(struct packed_ref_cache *packed_refs) +{ + packed_refs->referrers++; +} + +/* + * Decrease the reference count of *packed_refs. If it goes to zero, + * free *packed_refs and return true; otherwise return false. + */ +static int release_packed_ref_cache(struct packed_ref_cache *packed_refs) +{ + if (!--packed_refs->referrers) { + free_ref_entry(packed_refs->root); + stat_validity_clear(&packed_refs->validity); + free(packed_refs); + return 1; + } else { + return 0; + } +} + +static void clear_packed_ref_cache(struct files_ref_store *refs) +{ + if (refs->packed) { + struct packed_ref_cache *packed_refs = refs->packed; + + if (packed_refs->lock) + die("internal error: packed-ref cache cleared while locked"); + refs->packed = NULL; + release_packed_ref_cache(packed_refs); + } +} + +static void clear_loose_ref_cache(struct files_ref_store *refs) +{ + if (refs->loose) { + free_ref_entry(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(const char *submodule) +{ + struct files_ref_store *refs = xcalloc(1, sizeof(*refs)); + struct ref_store *ref_store = (struct ref_store *)refs; + + base_ref_store_init(ref_store, &refs_be_files); + + refs->submodule = xstrdup_or_null(submodule); + + return ref_store; +} + +/* + * Die if refs is for a submodule (i.e., not for the main repository). + * caller is used in any necessary error messages. + */ +static void files_assert_main_repository(struct files_ref_store *refs, + const char *caller) +{ + if (refs->submodule) + die("BUG: %s called for a submodule", caller); +} + +/* + * Downcast ref_store to files_ref_store. Die if ref_store is not a + * files_ref_store. If submodule_allowed is not true, then also die if + * files_ref_store is for a submodule (i.e., not for the main + * repository). caller is used in any necessary error messages. + */ +static struct files_ref_store *files_downcast( + struct ref_store *ref_store, int submodule_allowed, + const char *caller) +{ + struct files_ref_store *refs; + + if (ref_store->be != &refs_be_files) + die("BUG: ref_store is type \"%s\" not \"files\" in %s", + ref_store->be->name, caller); + + refs = (struct files_ref_store *)ref_store; + + if (!submodule_allowed) + files_assert_main_repository(refs, caller); + + return refs; +} + +/* The length of a peeled reference line in packed-refs, including EOL: */ +#define PEELED_LINE_LENGTH 42 + +/* + * The packed-refs header line that we write out. Perhaps other + * traits will be added later. The trailing space is required. + */ +static const char PACKED_REFS_HEADER[] = + "# pack-refs with: peeled fully-peeled \n"; + +/* + * Parse one line from a packed-refs file. Write the SHA1 to sha1. + * Return a pointer to the refname within the line (null-terminated), + * or NULL if there was a problem. + */ +static const char *parse_ref_line(struct strbuf *line, unsigned char *sha1) +{ + const char *ref; + + /* + * 42: the answer to everything. + * + * In this case, it happens to be the answer to + * 40 (length of sha1 hex representation) + * +1 (space in between hex and name) + * +1 (newline at the end of the line) + */ + if (line->len <= 42) + return NULL; + + if (get_sha1_hex(line->buf, sha1) < 0) + return NULL; + if (!isspace(line->buf[40])) + return NULL; + + ref = line->buf + 41; + if (isspace(*ref)) + return NULL; + + if (line->buf[line->len - 1] != '\n') + return NULL; + line->buf[--line->len] = 0; + + return ref; +} + +/* + * Read f, which is a packed-refs file, into dir. + * + * A comment line of the form "# pack-refs with: " may contain zero or + * more traits. We interpret the traits as follows: + * + * No traits: + * + * 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). + */ +static void read_packed_refs(FILE *f, struct ref_dir *dir) +{ + struct ref_entry *last = NULL; + struct strbuf line = STRBUF_INIT; + enum { PEELED_NONE, PEELED_TAGS, PEELED_FULLY } peeled = PEELED_NONE; + + while (strbuf_getwholeline(&line, f, '\n') != EOF) { + unsigned char sha1[20]; + const char *refname; + const char *traits; + + if (skip_prefix(line.buf, "# pack-refs with:", &traits)) { + if (strstr(traits, " fully-peeled ")) + peeled = PEELED_FULLY; + else if (strstr(traits, " peeled ")) + peeled = PEELED_TAGS; + /* perhaps other traits later as well */ + continue; + } + + refname = parse_ref_line(&line, sha1); + if (refname) { + int flag = REF_ISPACKED; + + if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) { + if (!refname_is_safe(refname)) + die("packed refname is dangerous: %s", refname); + hashclr(sha1); + flag |= REF_BAD_NAME | REF_ISBROKEN; + } + last = create_ref_entry(refname, sha1, flag, 0); + if (peeled == PEELED_FULLY || + (peeled == PEELED_TAGS && starts_with(refname, "refs/tags/"))) + last->flag |= REF_KNOWS_PEELED; + add_ref(dir, last); + continue; + } + if (last && + line.buf[0] == '^' && + line.len == PEELED_LINE_LENGTH && + line.buf[PEELED_LINE_LENGTH - 1] == '\n' && + !get_sha1_hex(line.buf + 1, sha1)) { + hashcpy(last->u.value.peeled.hash, sha1); + /* + * Regardless of what the file header said, + * we definitely know the value of *this* + * reference: + */ + last->flag |= REF_KNOWS_PEELED; + } + } + + strbuf_release(&line); +} + +/* + * Get the packed_ref_cache for the specified files_ref_store, + * creating it if necessary. + */ +static struct packed_ref_cache *get_packed_ref_cache(struct files_ref_store *refs) +{ + char *packed_refs_file; + + if (refs->submodule) + packed_refs_file = git_pathdup_submodule(refs->submodule, + "packed-refs"); + else + packed_refs_file = git_pathdup("packed-refs"); + + if (refs->packed && + !stat_validity_check(&refs->packed->validity, packed_refs_file)) + clear_packed_ref_cache(refs); + + if (!refs->packed) { + FILE *f; + + refs->packed = xcalloc(1, sizeof(*refs->packed)); + acquire_packed_ref_cache(refs->packed); + refs->packed->root = create_dir_entry(refs, "", 0, 0); + f = fopen(packed_refs_file, "r"); + if (f) { + stat_validity_update(&refs->packed->validity, fileno(f)); + read_packed_refs(f, get_ref_dir(refs->packed->root)); + fclose(f); + } + } + free(packed_refs_file); + return refs->packed; +} + +static struct ref_dir *get_packed_ref_dir(struct packed_ref_cache *packed_ref_cache) +{ + return get_ref_dir(packed_ref_cache->root); +} + +static struct ref_dir *get_packed_refs(struct files_ref_store *refs) +{ + return get_packed_ref_dir(get_packed_ref_cache(refs)); +} + +/* + * Add a reference to the in-memory packed reference cache. This may + * only be called while the packed-refs file is locked (see + * lock_packed_refs()). To actually write the packed-refs file, call + * commit_packed_refs(). + */ +static void add_packed_ref(struct files_ref_store *refs, + const char *refname, const unsigned char *sha1) +{ + struct packed_ref_cache *packed_ref_cache = get_packed_ref_cache(refs); + + if (!packed_ref_cache->lock) + die("internal error: packed refs not locked"); + add_ref(get_packed_ref_dir(packed_ref_cache), + create_ref_entry(refname, sha1, REF_ISPACKED, 1)); +} + +/* + * 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 read_loose_refs(const char *dirname, struct ref_dir *dir) +{ + struct files_ref_store *refs = dir->ref_store; + DIR *d; + struct dirent *de; + int dirnamelen = strlen(dirname); + struct strbuf refname; + struct strbuf path = STRBUF_INIT; + size_t path_baselen; + int err = 0; + + if (refs->submodule) + err = strbuf_git_path_submodule(&path, refs->submodule, "%s", dirname); + else + strbuf_git_path(&path, "%s", dirname); + path_baselen = path.len; + + if (err) { + strbuf_release(&path); + return; + } + + 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) { + unsigned char sha1[20]; + 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(refs, refname.buf, + refname.len, 1)); + } else { + if (!resolve_ref_recursively(&refs->base, + refname.buf, + RESOLVE_REF_READING, + sha1, &flag)) { + hashclr(sha1); + flag |= REF_ISBROKEN; + } else if (is_null_sha1(sha1)) { + /* + * It is so astronomically unlikely + * that NULL_SHA1 is the SHA-1 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); + hashclr(sha1); + flag |= REF_BAD_NAME | REF_ISBROKEN; + } + add_entry_to_dir(dir, + create_ref_entry(refname.buf, sha1, flag, 0)); + } + strbuf_setlen(&refname, dirnamelen); + strbuf_setlen(&path, path_baselen); + } + strbuf_release(&refname); + strbuf_release(&path); + closedir(d); +} + +static struct ref_dir *get_loose_refs(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_dir_entry(refs, "", 0, 0); + /* + * Create an incomplete entry for "refs/": + */ + add_entry_to_dir(get_ref_dir(refs->loose), + create_dir_entry(refs, "refs/", 5, 1)); + } + return get_ref_dir(refs->loose); +} + +/* + * Return the ref_entry for the given refname from the packed + * references. If it does not exist, return NULL. + */ +static struct ref_entry *get_packed_ref(struct files_ref_store *refs, + const char *refname) +{ + return find_ref(get_packed_refs(refs), refname); +} + +/* + * A loose ref file doesn't exist; check for a packed ref. + */ +static int resolve_packed_ref(struct files_ref_store *refs, + const char *refname, + unsigned char *sha1, unsigned int *flags) +{ + struct ref_entry *entry; + + /* + * The loose reference file does not exist; check for a packed + * reference. + */ + entry = get_packed_ref(refs, refname); + if (entry) { + hashcpy(sha1, entry->u.value.oid.hash); + *flags |= REF_ISPACKED; + return 0; + } + /* refname is not a packed reference. */ + return -1; +} + +static int files_read_raw_ref(struct ref_store *ref_store, + const char *refname, unsigned char *sha1, + struct strbuf *referent, unsigned int *type) +{ + struct files_ref_store *refs = + files_downcast(ref_store, 1, "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 save_errno; + int remaining_retries = 3; + + *type = 0; + strbuf_reset(&sb_path); + + if (refs->submodule) + strbuf_git_path_submodule(&sb_path, refs->submodule, "%s", refname); + else + strbuf_git_path(&sb_path, "%s", 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) { + if (errno != ENOENT) + goto out; + if (resolve_packed_ref(refs, refname, sha1, type)) { + errno = 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, 0) < 0) { + if (errno == ENOENT || errno == 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)) { + /* + * Even though there is a directory where the loose + * ref is supposed to be, there could still be a + * packed ref: + */ + if (resolve_packed_ref(refs, refname, sha1, type)) { + errno = 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) { + if (errno == 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) { + int save_errno = errno; + close(fd); + errno = save_errno; + goto out; + } + close(fd); + strbuf_rtrim(&sb_contents); + buf = sb_contents.buf; + if (starts_with(buf, "ref:")) { + buf += 4; + while (isspace(*buf)) + buf++; + + strbuf_reset(referent); + strbuf_addstr(referent, buf); + *type |= REF_ISSYMREF; + ret = 0; + goto out; + } + + /* + * Please note that FETCH_HEAD has additional + * data after the sha. + */ + if (get_sha1_hex(buf, sha1) || + (buf[40] != '\0' && !isspace(buf[40]))) { + *type |= REF_ISBROKEN; + errno = EINVAL; + goto out; + } + + ret = 0; + +out: + save_errno = errno; + strbuf_release(&sb_path); + strbuf_release(&sb_contents); + errno = save_errno; + 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(struct files_ref_store *refs, + 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); + 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 = 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 (files_read_raw_ref(&refs->base, 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(refs), + 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(refs), + 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 + * value that is already stored in it. + * + * It is OK to call this function with a packed reference entry that + * might be stale and might even refer to an object that has since + * been garbage-collected. In such a case, if the entry has + * REF_KNOWS_PEELED then leave the status unchanged and return + * PEEL_PEELED or PEEL_NON_TAG; otherwise, return PEEL_INVALID. + */ +static enum peel_status peel_entry(struct ref_entry *entry, int repeel) +{ + enum peel_status status; + + if (entry->flag & REF_KNOWS_PEELED) { + if (repeel) { + entry->flag &= ~REF_KNOWS_PEELED; + oidclr(&entry->u.value.peeled); + } else { + return is_null_oid(&entry->u.value.peeled) ? + PEEL_NON_TAG : PEEL_PEELED; + } + } + if (entry->flag & REF_ISBROKEN) + return PEEL_BROKEN; + if (entry->flag & REF_ISSYMREF) + return PEEL_IS_SYMREF; + + status = peel_object(entry->u.value.oid.hash, entry->u.value.peeled.hash); + if (status == PEEL_PEELED || status == PEEL_NON_TAG) + entry->flag |= REF_KNOWS_PEELED; + return status; +} + +static int files_peel_ref(struct ref_store *ref_store, + const char *refname, unsigned char *sha1) +{ + struct files_ref_store *refs = files_downcast(ref_store, 0, "peel_ref"); + int flag; + unsigned char base[20]; + + 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, peeled.hash); + return 0; + } + + if (read_ref_full(refname, RESOLVE_REF_READING, base, &flag)) + return -1; + + /* + * If the reference is packed, read its ref_entry from the + * cache in the hope that we already know its peeled value. + * We only try this optimization on packed references because + * (a) forcing the filling of the loose reference cache could + * be expensive and (b) loose references anyway usually do not + * have REF_KNOWS_PEELED. + */ + if (flag & REF_ISPACKED) { + struct ref_entry *r = get_packed_ref(refs, refname); + if (r) { + if (peel_entry(r, 0)) + return -1; + hashcpy(sha1, r->u.value.peeled.hash); + return 0; + } + } + + return peel_object(base, sha1); +} + +struct files_ref_iterator { + struct ref_iterator base; + + struct packed_ref_cache *packed_ref_cache; + struct ref_iterator *iter0; + 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 && + ref_type(iter->iter0->refname) != REF_TYPE_PER_WORKTREE) + continue; + + 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; + } + + 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); + + release_packed_ref_cache(iter->packed_ref_cache); + base_ref_iterator_free(ref_iterator); + return ok; +} + +static struct ref_iterator_vtable files_ref_iterator_vtable = { + files_ref_iterator_advance, + files_ref_iterator_peel, + 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 = + files_downcast(ref_store, 1, "ref_iterator_begin"); + 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) + flags |= DO_FOR_EACH_INCLUDE_BROKEN; + + iter = xcalloc(1, sizeof(*iter)); + ref_iterator = &iter->base; + base_ref_iterator_init(ref_iterator, &files_ref_iterator_vtable); + + /* + * 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; +} + +/* + * Verify that the reference locked by lock has the value old_sha1. + * Fail if the reference doesn't exist and mustexist is set. Return 0 + * on success. On error, write an error message to err, set errno, and + * return a negative value. + */ +static int verify_lock(struct ref_lock *lock, + const unsigned char *old_sha1, int mustexist, + struct strbuf *err) +{ + assert(err); + + if (read_ref_full(lock->ref_name, + mustexist ? RESOLVE_REF_READING : 0, + lock->old_oid.hash, NULL)) { + if (old_sha1) { + int save_errno = errno; + strbuf_addf(err, "can't verify ref '%s'", lock->ref_name); + errno = save_errno; + return -1; + } else { + 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", + lock->ref_name, + oid_to_hex(&lock->old_oid), + sha1_to_hex(old_sha1)); + errno = EBUSY; + return -1; + } + return 0; +} + +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(lk, path, LOCK_NO_DEREF) < 0 ? -1 : 0; +} + +/* + * Locks a ref returning the lock on success and NULL on failure. + * On failure errno is set to something meaningful. + */ +static struct ref_lock *lock_ref_sha1_basic(struct files_ref_store *refs, + const char *refname, + const unsigned char *old_sha1, + const struct string_list *extras, + const struct string_list *skip, + unsigned int flags, int *type, + struct strbuf *err) +{ + struct strbuf ref_file = STRBUF_INIT; + struct ref_lock *lock; + int last_errno = 0; + int mustexist = (old_sha1 && !is_null_sha1(old_sha1)); + int resolve_flags = RESOLVE_REF_NO_RECURSE; + int resolved; + + files_assert_main_repository(refs, "lock_ref_sha1_basic"); + assert(err); + + lock = xcalloc(1, sizeof(struct ref_lock)); + + if (mustexist) + resolve_flags |= RESOLVE_REF_READING; + if (flags & REF_DELETING) + resolve_flags |= RESOLVE_REF_ALLOW_BAD_NAME; + + 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. + */ + if (remove_empty_directories(&ref_file)) { + last_errno = errno; + if (!verify_refname_available_dir( + refname, extras, skip, + get_loose_refs(refs), err)) + strbuf_addf(err, "there are still refs under '%s'", + refname); + goto error_return; + } + resolved = !!resolve_ref_unsafe(refname, resolve_flags, + lock->old_oid.hash, type); + } + if (!resolved) { + last_errno = errno; + if (last_errno != ENOTDIR || + !verify_refname_available_dir( + refname, extras, skip, + get_loose_refs(refs), err)) + strbuf_addf(err, "unable to resolve reference '%s': %s", + refname, strerror(last_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 (is_null_oid(&lock->old_oid) && + verify_refname_available_dir(refname, extras, skip, + get_packed_refs(refs), + err)) { + last_errno = ENOTDIR; + goto error_return; + } + + lock->lk = xcalloc(1, sizeof(struct lock_file)); + + lock->ref_name = xstrdup(refname); + + if (raceproof_create_file(ref_file.buf, create_reflock, lock->lk)) { + last_errno = errno; + unable_to_lock_message(ref_file.buf, errno, err); + goto error_return; + } + + if (verify_lock(lock, old_sha1, mustexist, err)) { + last_errno = errno; + goto error_return; + } + goto out; + + error_return: + unlock_ref(lock); + lock = NULL; + + out: + strbuf_release(&ref_file); + errno = last_errno; + return lock; +} + +/* + * 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. + */ +static void write_packed_entry(FILE *fh, char *refname, unsigned char *sha1, + unsigned char *peeled) +{ + fprintf_or_die(fh, "%s %s\n", sha1_to_hex(sha1), refname); + if (peeled) + fprintf_or_die(fh, "^%s\n", sha1_to_hex(peeled)); +} + +/* + * An each_ref_entry_fn that writes the entry to a packed-refs file. + */ +static int write_packed_entry_fn(struct ref_entry *entry, void *cb_data) +{ + enum peel_status peel_status = peel_entry(entry, 0); + + if (peel_status != PEEL_PEELED && peel_status != PEEL_NON_TAG) + error("internal error: %s is not a valid packed reference!", + entry->name); + write_packed_entry(cb_data, entry->name, entry->u.value.oid.hash, + peel_status == PEEL_PEELED ? + entry->u.value.peeled.hash : NULL); + return 0; +} + +/* + * Lock the packed-refs file for writing. Flags is passed to + * hold_lock_file_for_update(). Return 0 on success. On errors, set + * errno appropriately and return a nonzero value. + */ +static int lock_packed_refs(struct files_ref_store *refs, int flags) +{ + static int timeout_configured = 0; + static int timeout_value = 1000; + struct packed_ref_cache *packed_ref_cache; + + files_assert_main_repository(refs, "lock_packed_refs"); + + if (!timeout_configured) { + git_config_get_int("core.packedrefstimeout", &timeout_value); + timeout_configured = 1; + } + + if (hold_lock_file_for_update_timeout( + &packlock, git_path("packed-refs"), + flags, timeout_value) < 0) + return -1; + /* + * Get the current packed-refs while holding the lock. If the + * packed-refs file has been modified since we last read it, + * this will automatically invalidate the cache and re-read + * the packed-refs file. + */ + packed_ref_cache = get_packed_ref_cache(refs); + packed_ref_cache->lock = &packlock; + /* Increment the reference count to prevent it from being freed: */ + acquire_packed_ref_cache(packed_ref_cache); + return 0; +} + +/* + * Write the current version of the packed refs cache from memory to + * disk. The packed-refs file must already be locked for writing (see + * lock_packed_refs()). Return zero on success. On errors, set errno + * and return a nonzero value + */ +static int commit_packed_refs(struct files_ref_store *refs) +{ + struct packed_ref_cache *packed_ref_cache = + get_packed_ref_cache(refs); + int error = 0; + int save_errno = 0; + FILE *out; + + files_assert_main_repository(refs, "commit_packed_refs"); + + if (!packed_ref_cache->lock) + die("internal error: packed-refs not locked"); + + out = fdopen_lock_file(packed_ref_cache->lock, "w"); + if (!out) + die_errno("unable to fdopen packed-refs descriptor"); + + fprintf_or_die(out, "%s", PACKED_REFS_HEADER); + do_for_each_entry_in_dir(get_packed_ref_dir(packed_ref_cache), + 0, write_packed_entry_fn, out); + + if (commit_lock_file(packed_ref_cache->lock)) { + save_errno = errno; + error = -1; + } + packed_ref_cache->lock = NULL; + release_packed_ref_cache(packed_ref_cache); + errno = save_errno; + return error; +} + +/* + * Rollback the lockfile for the packed-refs file, and discard the + * in-memory packed reference cache. (The packed-refs file will be + * read anew if it is needed again after this function is called.) + */ +static void rollback_packed_refs(struct files_ref_store *refs) +{ + struct packed_ref_cache *packed_ref_cache = + get_packed_ref_cache(refs); + + files_assert_main_repository(refs, "rollback_packed_refs"); + + if (!packed_ref_cache->lock) + die("internal error: packed-refs not locked"); + rollback_lock_file(packed_ref_cache->lock); + packed_ref_cache->lock = NULL; + release_packed_ref_cache(packed_ref_cache); + clear_packed_ref_cache(refs); +} + +struct ref_to_prune { + struct ref_to_prune *next; + unsigned char sha1[20]; + char name[FLEX_ARRAY]; +}; + +struct pack_refs_cb_data { + unsigned int flags; + struct ref_dir *packed_refs; + struct ref_to_prune *ref_to_prune; +}; + +/* + * An each_ref_entry_fn that is run over loose references only. 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 + * ref_to_prune in the pack_refs_cb_data. + */ +static int pack_if_possible_fn(struct ref_entry *entry, void *cb_data) +{ + struct pack_refs_cb_data *cb = cb_data; + enum peel_status peel_status; + struct ref_entry *packed_entry; + int is_tag_ref = starts_with(entry->name, "refs/tags/"); + + /* Do not pack per-worktree refs: */ + if (ref_type(entry->name) != REF_TYPE_NORMAL) + return 0; + + /* ALWAYS pack tags */ + if (!(cb->flags & PACK_REFS_ALL) && !is_tag_ref) + return 0; + + /* Do not pack symbolic or broken refs: */ + if ((entry->flag & REF_ISSYMREF) || !entry_resolves_to_object(entry)) + return 0; + + /* Add a packed ref cache entry equivalent to the loose entry. */ + peel_status = peel_entry(entry, 1); + if (peel_status != PEEL_PEELED && peel_status != PEEL_NON_TAG) + die("internal error peeling reference %s (%s)", + entry->name, oid_to_hex(&entry->u.value.oid)); + packed_entry = find_ref(cb->packed_refs, entry->name); + if (packed_entry) { + /* Overwrite existing packed entry with info from loose entry */ + packed_entry->flag = REF_ISPACKED | REF_KNOWS_PEELED; + oidcpy(&packed_entry->u.value.oid, &entry->u.value.oid); + } else { + packed_entry = create_ref_entry(entry->name, entry->u.value.oid.hash, + REF_ISPACKED | REF_KNOWS_PEELED, 0); + add_ref(cb->packed_refs, packed_entry); + } + oidcpy(&packed_entry->u.value.peeled, &entry->u.value.peeled); + + /* Schedule the loose reference for pruning if requested. */ + if ((cb->flags & PACK_REFS_PRUNE)) { + struct ref_to_prune *n; + FLEX_ALLOC_STR(n, name, entry->name); + hashcpy(n->sha1, entry->u.value.oid.hash); + n->next = cb->ref_to_prune; + cb->ref_to_prune = n; + } + return 0; +} + +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(const char *refname, unsigned int flags) +{ + struct strbuf buf = 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); + if ((flags & REMOVE_EMPTY_PARENTS_REF) && + rmdir(git_path("%s", buf.buf))) + flags &= ~REMOVE_EMPTY_PARENTS_REF; + if ((flags & REMOVE_EMPTY_PARENTS_REFLOG) && + rmdir(git_path("logs/%s", buf.buf))) + flags &= ~REMOVE_EMPTY_PARENTS_REFLOG; + } + strbuf_release(&buf); +} + +/* make sure nobody touched the ref, and unlink */ +static void prune_ref(struct ref_to_prune *r) +{ + struct ref_transaction *transaction; + struct strbuf err = STRBUF_INIT; + + if (check_refname_format(r->name, 0)) + return; + + transaction = ref_transaction_begin(&err); + if (!transaction || + ref_transaction_delete(transaction, r->name, r->sha1, + REF_ISPRUNING | REF_NODEREF, NULL, &err) || + ref_transaction_commit(transaction, &err)) { + ref_transaction_free(transaction); + error("%s", err.buf); + strbuf_release(&err); + return; + } + ref_transaction_free(transaction); + strbuf_release(&err); +} + +static void prune_refs(struct ref_to_prune *r) +{ + while (r) { + prune_ref(r); + r = r->next; + } +} + +static int files_pack_refs(struct ref_store *ref_store, unsigned int flags) +{ + struct files_ref_store *refs = + files_downcast(ref_store, 0, "pack_refs"); + struct pack_refs_cb_data cbdata; + + memset(&cbdata, 0, sizeof(cbdata)); + cbdata.flags = flags; + + lock_packed_refs(refs, LOCK_DIE_ON_ERROR); + cbdata.packed_refs = get_packed_refs(refs); + + do_for_each_entry_in_dir(get_loose_refs(refs), 0, + pack_if_possible_fn, &cbdata); + + if (commit_packed_refs(refs)) + die_errno("unable to overwrite old ref-pack file"); + + prune_refs(cbdata.ref_to_prune); + return 0; +} + +/* + * Rewrite the packed-refs file, omitting any refs listed in + * 'refnames'. On error, leave packed-refs unchanged, write an error + * message to 'err', and return a nonzero value. + * + * The refs in 'refnames' needn't be sorted. `err` must not be NULL. + */ +static int repack_without_refs(struct files_ref_store *refs, + struct string_list *refnames, struct strbuf *err) +{ + struct ref_dir *packed; + struct string_list_item *refname; + int ret, needs_repacking = 0, removed = 0; + + files_assert_main_repository(refs, "repack_without_refs"); + assert(err); + + /* Look for a packed ref */ + for_each_string_list_item(refname, refnames) { + if (get_packed_ref(refs, refname->string)) { + needs_repacking = 1; + break; + } + } + + /* Avoid locking if we have nothing to do */ + if (!needs_repacking) + return 0; /* no refname exists in packed refs */ + + if (lock_packed_refs(refs, 0)) { + unable_to_lock_message(git_path("packed-refs"), errno, err); + return -1; + } + packed = get_packed_refs(refs); + + /* Remove refnames from the cache */ + for_each_string_list_item(refname, refnames) + if (remove_entry(packed, refname->string) != -1) + removed = 1; + if (!removed) { + /* + * All packed entries disappeared while we were + * acquiring the lock. + */ + rollback_packed_refs(refs); + return 0; + } + + /* Write what remains */ + ret = commit_packed_refs(refs); + if (ret) + strbuf_addf(err, "unable to overwrite old ref-pack file: %s", + strerror(errno)); + return ret; +} + +static int files_delete_refs(struct ref_store *ref_store, + struct string_list *refnames, unsigned int flags) +{ + struct files_ref_store *refs = + files_downcast(ref_store, 0, "delete_refs"); + struct strbuf err = STRBUF_INIT; + int i, result = 0; + + if (!refnames->nr) + return 0; + + result = repack_without_refs(refs, refnames, &err); + if (result) { + /* + * 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); + + goto out; + } + + for (i = 0; i < refnames->nr; i++) { + const char *refname = refnames->items[i].string; + + if (delete_ref(NULL, refname, NULL, flags)) + result |= error(_("could not remove reference %s"), refname); + } + +out: + strbuf_release(&err); + return result; +} + +/* + * 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 "logs/refs/.tmp-renamed-log" + +static int rename_tmp_log_callback(const char *path, void *cb) +{ + int *true_errno = cb; + + if (rename(git_path(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. + */ + *true_errno = errno; + if (errno == ENOTDIR) + errno = EISDIR; + return -1; + } else { + return 0; + } +} + +static int rename_tmp_log(const char *newrefname) +{ + char *path = git_pathdup("logs/%s", newrefname); + int ret, true_errno; + + ret = raceproof_create_file(path, rename_tmp_log_callback, &true_errno); + if (ret) { + if (errno == EISDIR) + error("directory not empty: %s", path); + else + error("unable to move logfile %s to %s: %s", + git_path(TMP_RENAMED_LOG), path, + strerror(true_errno)); + } + + free(path); + return ret; +} + +static int files_verify_refname_available(struct ref_store *ref_store, + const char *newname, + const struct string_list *extras, + const struct string_list *skip, + struct strbuf *err) +{ + struct files_ref_store *refs = + files_downcast(ref_store, 1, "verify_refname_available"); + struct ref_dir *packed_refs = get_packed_refs(refs); + struct ref_dir *loose_refs = get_loose_refs(refs); + + if (verify_refname_available_dir(newname, extras, skip, + packed_refs, err) || + verify_refname_available_dir(newname, extras, skip, + loose_refs, err)) + return -1; + + return 0; +} + +static int write_ref_to_lockfile(struct ref_lock *lock, + const unsigned char *sha1, struct strbuf *err); +static int commit_ref_update(struct files_ref_store *refs, + struct ref_lock *lock, + const unsigned char *sha1, const char *logmsg, + struct strbuf *err); + +static int files_rename_ref(struct ref_store *ref_store, + const char *oldrefname, const char *newrefname, + const char *logmsg) +{ + struct files_ref_store *refs = + files_downcast(ref_store, 0, "rename_ref"); + unsigned char sha1[20], orig_sha1[20]; + int flag = 0, logmoved = 0; + struct ref_lock *lock; + struct stat loginfo; + int log = !lstat(git_path("logs/%s", oldrefname), &loginfo); + struct strbuf err = STRBUF_INIT; + + if (log && S_ISLNK(loginfo.st_mode)) + return error("reflog for %s is a symlink", oldrefname); + + 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 (!rename_ref_available(oldrefname, newrefname)) + return 1; + + if (log && rename(git_path("logs/%s", oldrefname), git_path(TMP_RENAMED_LOG))) + return error("unable to move logfile logs/%s to "TMP_RENAMED_LOG": %s", + oldrefname, strerror(errno)); + + if (delete_ref(logmsg, oldrefname, orig_sha1, REF_NODEREF)) { + error("unable to delete old %s", oldrefname); + goto rollback; + } + + /* + * 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(NULL, newrefname, NULL, REF_NODEREF)) { + if (errno == EISDIR) { + struct strbuf path = STRBUF_INIT; + int result; + + strbuf_git_path(&path, "%s", 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(newrefname)) + goto rollback; + + logmoved = log; + + lock = lock_ref_sha1_basic(refs, 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); + goto rollback; + } + hashcpy(lock->old_oid.hash, orig_sha1); + + if (write_ref_to_lockfile(lock, orig_sha1, &err) || + commit_ref_update(refs, lock, orig_sha1, logmsg, &err)) { + error("unable to write current sha1 into %s: %s", newrefname, err.buf); + strbuf_release(&err); + goto rollback; + } + + return 0; + + rollback: + lock = lock_ref_sha1_basic(refs, oldrefname, NULL, NULL, NULL, + REF_NODEREF, NULL, &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_sha1, &err) || + commit_ref_update(refs, lock, orig_sha1, 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(git_path("logs/%s", newrefname), git_path("logs/%s", oldrefname))) + error("unable to restore logfile %s from %s: %s", + oldrefname, newrefname, strerror(errno)); + if (!logmoved && log && + rename(git_path(TMP_RENAMED_LOG), git_path("logs/%s", oldrefname))) + error("unable to restore logfile %s from "TMP_RENAMED_LOG": %s", + oldrefname, strerror(errno)); + + return 1; +} + +static int close_ref(struct ref_lock *lock) +{ + if (close_lock_file(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(const char *refname, int force_create, + int *logfd, struct strbuf *err) +{ + char *logfile = git_pathdup("logs/%s", refname); + + 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, 0666); + 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, int force_create, + struct strbuf *err) +{ + int fd; + + /* Check validity (but we don't need the result): */ + files_downcast(ref_store, 0, "create_reflog"); + + if (log_ref_setup(refname, force_create, &fd, err)) + return -1; + + if (fd >= 0) + close(fd); + + return 0; +} + +static int log_ref_write_fd(int fd, const unsigned char *old_sha1, + const unsigned char *new_sha1, + const char *committer, const char *msg) +{ + int msglen, written; + unsigned maxlen, len; + char *logrec; + + msglen = msg ? strlen(msg) : 0; + maxlen = strlen(committer) + msglen + 100; + logrec = xmalloc(maxlen); + len = xsnprintf(logrec, maxlen, "%s %s %s\n", + sha1_to_hex(old_sha1), + sha1_to_hex(new_sha1), + committer); + if (msglen) + len += copy_reflog_msg(logrec + len - 1, msg) - 1; + + written = len <= maxlen ? write_in_full(fd, logrec, len) : -1; + free(logrec); + if (written != len) + return -1; + + return 0; +} + +int files_log_ref_write(const char *refname, const unsigned char *old_sha1, + const unsigned char *new_sha1, 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(refname, flags & REF_FORCE_CREATE_REFLOG, + &logfd, err); + + if (result) + return result; + + if (logfd < 0) + return 0; + result = log_ref_write_fd(logfd, old_sha1, new_sha1, + git_committer_info(0), msg); + if (result) { + int save_errno = errno; + + strbuf_addf(err, "unable to append to '%s': %s", + git_path("logs/%s", refname), strerror(save_errno)); + close(logfd); + return -1; + } + if (close(logfd)) { + int save_errno = errno; + + strbuf_addf(err, "unable to append to '%s': %s", + git_path("logs/%s", refname), strerror(save_errno)); + return -1; + } + return 0; +} + +/* + * Write sha1 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 unsigned char *sha1, struct strbuf *err) +{ + static char term = '\n'; + struct object *o; + int fd; + + o = parse_object(sha1); + if (!o) { + strbuf_addf(err, + "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'", + sha1_to_hex(sha1), lock->ref_name); + unlock_ref(lock); + return -1; + } + fd = get_lock_file_fd(lock->lk); + if (write_in_full(fd, sha1_to_hex(sha1), 40) != 40 || + write_in_full(fd, &term, 1) != 1 || + close_ref(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 unsigned char *sha1, const char *logmsg, + struct strbuf *err) +{ + files_assert_main_repository(refs, "commit_ref_update"); + + clear_loose_ref_cache(refs); + if (files_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", + 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). + */ + 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) && + !strcmp(head_ref, lock->ref_name)) { + struct strbuf log_err = STRBUF_INIT; + if (files_log_ref_write("HEAD", lock->old_oid.hash, sha1, + 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 ref_lock *lock, const char *refname, + const char *target, const char *logmsg) +{ + struct strbuf err = STRBUF_INIT; + unsigned char new_sha1[20]; + if (logmsg && !read_ref(target, new_sha1) && + files_log_ref_write(refname, lock->old_oid.hash, new_sha1, + logmsg, 0, &err)) { + error("%s", err.buf); + strbuf_release(&err); + } +} + +static int create_symref_locked(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(lock, refname, target, logmsg); + return 0; + } + + if (!fdopen_lock_file(lock->lk, "w")) + return error("unable to fdopen %s: %s", + lock->lk->tempfile.filename.buf, strerror(errno)); + + update_symref_reflog(lock, refname, target, logmsg); + + /* no error check; commit_ref will check ferror */ + fprintf(lock->lk->tempfile.fp, "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, 0, "create_symref"); + struct strbuf err = STRBUF_INIT; + struct ref_lock *lock; + int ret; + + lock = lock_ref_sha1_basic(refs, refname, NULL, + NULL, NULL, REF_NODEREF, NULL, + &err); + if (!lock) { + error("%s", err.buf); + strbuf_release(&err); + return -1; + } + + ret = create_symref_locked(lock, refname, target, logmsg); + unlock_ref(lock); + return ret; +} + +int set_worktree_head_symref(const char *gitdir, const char *target, const char *logmsg) +{ + static struct lock_file head_lock; + struct ref_lock *lock; + struct strbuf head_path = STRBUF_INIT; + const char *head_rel; + int ret; + + strbuf_addf(&head_path, "%s/HEAD", absolute_path(gitdir)); + if (hold_lock_file_for_update(&head_lock, head_path.buf, + LOCK_NO_DEREF) < 0) { + struct strbuf err = STRBUF_INIT; + unable_to_lock_message(head_path.buf, errno, &err); + error("%s", err.buf); + strbuf_release(&err); + strbuf_release(&head_path); + return -1; + } + + /* head_rel will be "HEAD" for the main tree, "worktrees/wt/HEAD" for + linked trees */ + head_rel = remove_leading_path(head_path.buf, + absolute_path(get_git_common_dir())); + /* to make use of create_symref_locked(), initialize ref_lock */ + lock = xcalloc(1, sizeof(struct ref_lock)); + lock->lk = &head_lock; + lock->ref_name = xstrdup(head_rel); + + ret = create_symref_locked(lock, head_rel, target, logmsg); + + unlock_ref(lock); /* will free lock */ + strbuf_release(&head_path); + return ret; +} + +static int files_reflog_exists(struct ref_store *ref_store, + const char *refname) +{ + struct stat st; + + /* Check validity (but we don't need the result): */ + files_downcast(ref_store, 0, "reflog_exists"); + + return !lstat(git_path("logs/%s", refname), &st) && + S_ISREG(st.st_mode); +} + +static int files_delete_reflog(struct ref_store *ref_store, + const char *refname) +{ + /* Check validity (but we don't need the result): */ + files_downcast(ref_store, 0, "delete_reflog"); + + return remove_path(git_path("logs/%s", refname)); +} + +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; + unsigned long 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 = strtoul(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 strbuf sb = STRBUF_INIT; + FILE *logfp; + long pos; + int ret = 0, at_tail = 1; + + /* Check validity (but we don't need the result): */ + files_downcast(ref_store, 0, "for_each_reflog_ent_reverse"); + + logfp = fopen(git_path("logs/%s", refname), "r"); + if (!logfp) + return -1; + + /* Jump to the end */ + if (fseek(logfp, 0, SEEK_END) < 0) + return 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)) + return error("cannot seek back reflog for %s: %s", + refname, strerror(errno)); + nread = fread(buf, cnt, 1, logfp); + if (nread != 1) + return error("cannot read %d bytes from reflog for %s: %s", + cnt, refname, strerror(errno)); + 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) + die("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) +{ + FILE *logfp; + struct strbuf sb = STRBUF_INIT; + int ret = 0; + + /* Check validity (but we don't need the result): */ + files_downcast(ref_store, 0, "for_each_reflog_ent"); + + logfp = fopen(git_path("logs/%s", refname), "r"); + 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 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 (read_ref_full(diter->relative_path, 0, + iter->oid.hash, &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, + 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 +}; + +static struct ref_iterator *files_reflog_iterator_begin(struct ref_store *ref_store) +{ + struct files_reflog_iterator *iter = xcalloc(1, sizeof(*iter)); + struct ref_iterator *ref_iterator = &iter->base; + + /* Check validity (but we don't need the result): */ + files_downcast(ref_store, 0, "reflog_iterator_begin"); + + base_ref_iterator_init(ref_iterator, &files_reflog_iterator_vtable); + iter->dir_iterator = dir_iterator_begin(git_path("logs")); + return ref_iterator; +} + +static int ref_update_reject_duplicates(struct string_list *refnames, + struct strbuf *err) +{ + int i, n = refnames->nr; + + assert(err); + + 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.", + 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 files_ref_store *refs, + 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 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_sha1(update->old_sha1); + int ret; + struct ref_lock *lock; + + files_assert_main_repository(refs, "lock_ref_for_update"); + + 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(refs, update->refname, mustexist, + affected_refnames, NULL, + &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; + } + + update->backend_data = 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(refs, 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) { + 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) && + !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->backend_data = 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; +} + +static int files_transaction_commit(struct ref_store *ref_store, + struct ref_transaction *transaction, + struct strbuf *err) +{ + struct files_ref_store *refs = + files_downcast(ref_store, 0, "ref_transaction_commit"); + int ret = 0, i; + 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 (!transaction->nr) { + transaction->state = REF_TRANSACTION_CLOSED; + return 0; + } + + /* + * 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; + 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 = 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 < 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; + } + + /* 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(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->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; + } + } + } + /* Perform deletes now that updates are safely completed */ + 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)) { + if (!(update->type & REF_ISPACKED) || + update->type & REF_ISSYMREF) { + /* It is a loose reference. */ + if (unlink_or_msg(git_path("%s", lock->ref_name), err)) { + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + update->flags |= REF_DELETED_LOOSE; + } + + if (!(update->flags & REF_ISPRUNING)) + string_list_append(&refs_to_delete, + lock->ref_name); + } + } + + if (repack_without_refs(refs, &refs_to_delete, err)) { + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + + /* Delete the reflogs of any references that were deleted: */ + for_each_string_list_item(ref_to_delete, &refs_to_delete) { + if (!unlink_or_warn(git_path("logs/%s", ref_to_delete->string))) + try_remove_empty_parents(ref_to_delete->string, + REMOVE_EMPTY_PARENTS_REFLOG); + } + + clear_loose_ref_cache(refs); + +cleanup: + transaction->state = REF_TRANSACTION_CLOSED; + + 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); + + if (update->flags & REF_DELETED_LOOSE) { + /* + * The loose 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(update->refname, + REMOVE_EMPTY_PARENTS_REF); + } + } + + string_list_clear(&refs_to_delete, 0); + free(head_ref); + string_list_clear(&affected_refnames, 0); + + return ret; +} + +static int ref_present(const char *refname, + const struct object_id *oid, int flags, 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, 0, "initial_ref_transaction_commit"); + int ret = 0, i; + struct string_list affected_refnames = STRING_LIST_INIT_NODUP; + + assert(err); + + if (transaction->state != REF_TRANSACTION_OPEN) + 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 < 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 (for_each_rawref(ref_present, &affected_refnames)) + die("BUG: initial ref transaction called with existing refs"); + + 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)) + die("BUG: initial ref transaction with old_sha1 set"); + if (verify_refname_available(update->refname, + &affected_refnames, NULL, + err)) { + ret = TRANSACTION_NAME_CONFLICT; + goto cleanup; + } + } + + if (lock_packed_refs(refs, 0)) { + strbuf_addf(err, "unable to lock packed-refs file: %s", + strerror(errno)); + 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_NEW) && + !is_null_sha1(update->new_sha1)) + add_packed_ref(refs, update->refname, update->new_sha1); + } + + if (commit_packed_refs(refs)) { + strbuf_addf(err, "unable to commit packed-refs file: %s", + strerror(errno)); + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + +cleanup: + transaction->state = REF_TRANSACTION_CLOSED; + string_list_clear(&affected_refnames, 0); + return ret; +} + +struct expire_reflog_cb { + unsigned int flags; + reflog_expiry_should_prune_fn *should_prune_fn; + void *policy_cb; + FILE *newlog; + struct object_id last_kept_oid; +}; + +static int expire_reflog_ent(struct object_id *ooid, struct object_id *noid, + const char *email, unsigned long timestamp, int tz, + const char *message, void *cb_data) +{ + struct expire_reflog_cb *cb = cb_data; + struct expire_reflog_policy_cb *policy_cb = cb->policy_cb; + + if (cb->flags & EXPIRE_REFLOGS_REWRITE) + ooid = &cb->last_kept_oid; + + if ((*cb->should_prune_fn)(ooid->hash, noid->hash, email, timestamp, tz, + message, policy_cb)) { + if (!cb->newlog) + printf("would prune %s", message); + else if (cb->flags & EXPIRE_REFLOGS_VERBOSE) + printf("prune %s", message); + } else { + if (cb->newlog) { + fprintf(cb->newlog, "%s %s %s %lu %+05d\t%s", + oid_to_hex(ooid), oid_to_hex(noid), + email, timestamp, tz, message); + oidcpy(&cb->last_kept_oid, noid); + } + if (cb->flags & EXPIRE_REFLOGS_VERBOSE) + printf("keep %s", message); + } + return 0; +} + +static int files_reflog_expire(struct ref_store *ref_store, + const char *refname, const unsigned char *sha1, + 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 files_ref_store *refs = + files_downcast(ref_store, 0, "reflog_expire"); + static struct lock_file reflog_lock; + struct expire_reflog_cb cb; + struct ref_lock *lock; + char *log_file; + int status = 0; + int type; + struct strbuf err = STRBUF_INIT; + + memset(&cb, 0, sizeof(cb)); + cb.flags = flags; + 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_sha1_basic(refs, refname, sha1, + NULL, NULL, REF_NODEREF, + &type, &err); + if (!lock) { + error("cannot lock ref '%s': %s", refname, err.buf); + strbuf_release(&err); + return -1; + } + if (!reflog_exists(refname)) { + unlock_ref(lock); + return 0; + } + + log_file = git_pathdup("logs/%s", refname); + if (!(flags & EXPIRE_REFLOGS_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, sha1, cb.policy_cb); + for_each_reflog_ent(refname, expire_reflog_ent, &cb); + (*cleanup_fn)(cb.policy_cb); + + if (!(flags & EXPIRE_REFLOGS_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 = (flags & EXPIRE_REFLOGS_UPDATE_REF) && + !(type & REF_ISSYMREF) && + !is_null_oid(&cb.last_kept_oid); + + if (close_lock_file(&reflog_lock)) { + status |= error("couldn't write %s: %s", log_file, + strerror(errno)); + } else if (update && + (write_in_full(get_lock_file_fd(lock->lk), + oid_to_hex(&cb.last_kept_oid), GIT_SHA1_HEXSZ) != GIT_SHA1_HEXSZ || + write_str_in_full(get_lock_file_fd(lock->lk), "\n") != 1 || + close_ref(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) +{ + /* Check validity (but we don't need the result): */ + files_downcast(ref_store, 0, "init_db"); + + /* + * Create .git/refs/{heads,tags} + */ + safe_create_dir(git_path("refs/heads"), 1); + safe_create_dir(git_path("refs/tags"), 1); + if (get_shared_repository()) { + adjust_shared_perm(git_path("refs/heads")); + adjust_shared_perm(git_path("refs/tags")); + } + return 0; +} + +struct ref_storage_be refs_be_files = { + NULL, + "files", + files_ref_store_create, + files_init_db, + files_transaction_commit, + files_initial_transaction_commit, + + files_pack_refs, + files_peel_ref, + files_create_symref, + files_delete_refs, + files_rename_ref, + + files_ref_iterator_begin, + files_read_raw_ref, + files_verify_refname_available, + + files_reflog_iterator_begin, + files_for_each_reflog_ent, + files_for_each_reflog_ent_reverse, + files_reflog_exists, + files_create_reflog, + files_delete_reflog, + files_reflog_expire +}; |