diff options
Diffstat (limited to 'sha1_file.c')
| -rw-r--r-- | sha1_file.c | 988 |
1 files changed, 644 insertions, 344 deletions
diff --git a/sha1_file.c b/sha1_file.c index 6dcae3882b..8e27db1bd2 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -7,6 +7,7 @@ * creation etc. */ #include "cache.h" +#include "string-list.h" #include "delta.h" #include "pack.h" #include "blob.h" @@ -18,6 +19,9 @@ #include "refs.h" #include "pack-revindex.h" #include "sha1-lookup.h" +#include "bulk-checkin.h" +#include "streaming.h" +#include "dir.h" #ifndef O_NOATIME #if defined(__linux__) && (defined(__i386__) || defined(__PPC__)) @@ -32,6 +36,9 @@ static inline uintmax_t sz_fmt(size_t s) { return s; } const unsigned char null_sha1[20]; +static const char *no_log_pack_access = "no_log_pack_access"; +static const char *log_pack_access; + /* * This is meant to hold a *small* number of objects that you would * want read_sha1_file() to be able to return, but yet you do not want @@ -53,6 +60,8 @@ static struct cached_object empty_tree = { 0 }; +static struct packed_git *last_found_pack; + static struct cached_object *find_cached_object(const unsigned char *sha1) { int i; @@ -118,8 +127,13 @@ int safe_create_leading_directories(char *path) } } else if (mkdir(path, 0777)) { - *pos = '/'; - return -1; + if (errno == EEXIST && + !stat(path, &st) && S_ISDIR(st.st_mode)) { + ; /* somebody created it since we checked */ + } else { + *pos = '/'; + return -1; + } } else if (adjust_shared_perm(path)) { *pos = '/'; @@ -225,7 +239,6 @@ char *sha1_pack_index_name(const unsigned char *sha1) struct alternate_object_database *alt_odb_list; static struct alternate_object_database **alt_odb_tail; -static void read_info_alternates(const char * alternates, int depth); static int git_open_noatime(const char *name); /* @@ -243,7 +256,7 @@ static int git_open_noatime(const char *name); * SHA1, an extra slash for the first level indirection, and the * terminating NUL. */ -static int link_alt_odb_entry(const char * entry, int len, const char * relative_base, int depth) +static int link_alt_odb_entry(const char *entry, const char *relative_base, int depth) { const char *objdir = get_object_directory(); struct alternate_object_database *ent; @@ -255,7 +268,7 @@ static int link_alt_odb_entry(const char * entry, int len, const char * relative strbuf_addstr(&pathbuf, real_path(relative_base)); strbuf_addch(&pathbuf, '/'); } - strbuf_add(&pathbuf, entry, len); + strbuf_addstr(&pathbuf, entry); normalize_path_copy(pathbuf.buf, pathbuf.buf); @@ -295,7 +308,7 @@ static int link_alt_odb_entry(const char * entry, int len, const char * relative return -1; } } - if (!memcmp(ent->base, objdir, pfxlen)) { + if (!strcmp(ent->base, objdir)) { free(ent); return -1; } @@ -313,10 +326,12 @@ static int link_alt_odb_entry(const char * entry, int len, const char * relative return 0; } -static void link_alt_odb_entries(const char *alt, const char *ep, int sep, +static void link_alt_odb_entries(const char *alt, int len, int sep, const char *relative_base, int depth) { - const char *cp, *last; + struct string_list entries = STRING_LIST_INIT_NODUP; + char *alt_copy; + int i; if (depth > 5) { error("%s: ignoring alternate object stores, nesting too deep.", @@ -324,33 +339,24 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep, return; } - last = alt; - while (last < ep) { - cp = last; - if (cp < ep && *cp == '#') { - while (cp < ep && *cp != sep) - cp++; - last = cp + 1; + alt_copy = xmemdupz(alt, len); + string_list_split_in_place(&entries, alt_copy, sep, -1); + for (i = 0; i < entries.nr; i++) { + const char *entry = entries.items[i].string; + if (entry[0] == '\0' || entry[0] == '#') continue; + if (!is_absolute_path(entry) && depth) { + error("%s: ignoring relative alternate object store %s", + relative_base, entry); + } else { + link_alt_odb_entry(entry, relative_base, depth); } - while (cp < ep && *cp != sep) - cp++; - if (last != cp) { - if (!is_absolute_path(last) && depth) { - error("%s: ignoring relative alternate object store %s", - relative_base, last); - } else { - link_alt_odb_entry(last, cp - last, - relative_base, depth); - } - } - while (cp < ep && *cp == sep) - cp++; - last = cp; } + string_list_clear(&entries, 0); + free(alt_copy); } -static void read_info_alternates(const char * relative_base, int depth) +void read_info_alternates(const char * relative_base, int depth) { char *map; size_t mapsz; @@ -374,7 +380,7 @@ static void read_info_alternates(const char * relative_base, int depth) map = xmmap(NULL, mapsz, PROT_READ, MAP_PRIVATE, fd, 0); close(fd); - link_alt_odb_entries(map, map + mapsz, '\n', relative_base, depth); + link_alt_odb_entries(map, mapsz, '\n', relative_base, depth); munmap(map, mapsz); } @@ -388,7 +394,7 @@ void add_to_alternates_file(const char *reference) if (commit_lock_file(lock)) die("could not close alternates file"); if (alt_odb_tail) - link_alt_odb_entries(alt, alt + strlen(alt), '\n', NULL, 0); + link_alt_odb_entries(alt, strlen(alt), '\n', NULL, 0); } void foreach_alt_odb(alt_odb_fn fn, void *cb) @@ -412,7 +418,7 @@ void prepare_alt_odb(void) if (!alt) alt = ""; alt_odb_tail = &alt_odb_list; - link_alt_odb_entries(alt, alt + strlen(alt), PATH_SEP, NULL, 0); + link_alt_odb_entries(alt, strlen(alt), PATH_SEP, NULL, 0); read_info_alternates(get_object_directory(), 0); } @@ -719,6 +725,8 @@ void free_pack_by_name(const char *pack_name) close_pack_index(p); free(p->bad_object_sha1); *pp = p->next; + if (last_found_pack == p) + last_found_pack = NULL; free(p); return; } @@ -726,6 +734,24 @@ void free_pack_by_name(const char *pack_name) } } +static unsigned int get_max_fd_limit(void) +{ +#ifdef RLIMIT_NOFILE + struct rlimit lim; + + if (getrlimit(RLIMIT_NOFILE, &lim)) + die_errno("cannot get RLIMIT_NOFILE"); + + return lim.rlim_cur; +#elif defined(_SC_OPEN_MAX) + return sysconf(_SC_OPEN_MAX); +#elif defined(OPEN_MAX) + return OPEN_MAX; +#else + return 1; /* see the caller ;-) */ +#endif +} + /* * Do not call this directly as this leaks p->pack_fd on error return; * call open_packed_git() instead. @@ -742,13 +768,7 @@ static int open_packed_git_1(struct packed_git *p) return error("packfile %s index unavailable", p->pack_name); if (!pack_max_fds) { - struct rlimit lim; - unsigned int max_fds; - - if (getrlimit(RLIMIT_NOFILE, &lim)) - die_errno("cannot get RLIMIT_NOFILE"); - - max_fds = lim.rlim_cur; + unsigned int max_fds = get_max_fd_limit(); /* Save 3 for stdin/stdout/stderr, 22 for work */ if (25 < max_fds) @@ -989,6 +1009,63 @@ void install_packed_git(struct packed_git *pack) packed_git = pack; } +void (*report_garbage)(const char *desc, const char *path); + +static void report_helper(const struct string_list *list, + int seen_bits, int first, int last) +{ + const char *msg; + switch (seen_bits) { + case 0: + msg = "no corresponding .idx nor .pack"; + break; + case 1: + msg = "no corresponding .idx"; + break; + case 2: + msg = "no corresponding .pack"; + break; + default: + return; + } + for (; first < last; first++) + report_garbage(msg, list->items[first].string); +} + +static void report_pack_garbage(struct string_list *list) +{ + int i, baselen = -1, first = 0, seen_bits = 0; + + if (!report_garbage) + return; + + sort_string_list(list); + + for (i = 0; i < list->nr; i++) { + const char *path = list->items[i].string; + if (baselen != -1 && + strncmp(path, list->items[first].string, baselen)) { + report_helper(list, seen_bits, first, i); + baselen = -1; + seen_bits = 0; + } + if (baselen == -1) { + const char *dot = strrchr(path, '.'); + if (!dot) { + report_garbage("garbage found", path); + continue; + } + baselen = dot - path + 1; + first = i; + } + if (!strcmp(path + baselen, "pack")) + seen_bits |= 1; + else if (!strcmp(path + baselen, "idx")) + seen_bits |= 2; + } + report_helper(list, seen_bits, first, list->nr); +} + static void prepare_packed_git_one(char *objdir, int local) { /* Ensure that this buffer is large enough so that we can @@ -998,6 +1075,7 @@ static void prepare_packed_git_one(char *objdir, int local) int len; DIR *dir; struct dirent *de; + struct string_list garbage = STRING_LIST_INIT_DUP; sprintf(path, "%s/pack", objdir); len = strlen(path); @@ -1013,29 +1091,49 @@ static void prepare_packed_git_one(char *objdir, int local) int namelen = strlen(de->d_name); struct packed_git *p; - if (!has_extension(de->d_name, ".idx")) + if (len + namelen + 1 > sizeof(path)) { + if (report_garbage) { + struct strbuf sb = STRBUF_INIT; + strbuf_addf(&sb, "%.*s/%s", len - 1, path, de->d_name); + report_garbage("path too long", sb.buf); + strbuf_release(&sb); + } continue; + } - if (len + namelen + 1 > sizeof(path)) + if (is_dot_or_dotdot(de->d_name)) continue; - /* Don't reopen a pack we already have. */ strcpy(path + len, de->d_name); - for (p = packed_git; p; p = p->next) { - if (!memcmp(path, p->pack_name, len + namelen - 4)) - break; + + if (has_extension(de->d_name, ".idx")) { + /* Don't reopen a pack we already have. */ + for (p = packed_git; p; p = p->next) { + if (!memcmp(path, p->pack_name, len + namelen - 4)) + break; + } + if (p == NULL && + /* + * See if it really is a valid .idx file with + * corresponding .pack file that we can map. + */ + (p = add_packed_git(path, len + namelen, local)) != NULL) + install_packed_git(p); } - if (p) - continue; - /* See if it really is a valid .idx file with corresponding - * .pack file that we can map. - */ - p = add_packed_git(path, len + namelen, local); - if (!p) + + if (!report_garbage) continue; - install_packed_git(p); + + if (has_extension(de->d_name, ".idx") || + has_extension(de->d_name, ".pack") || + has_extension(de->d_name, ".keep")) + string_list_append(&garbage, path); + else + report_garbage("garbage found", path); } closedir(dir); + report_pack_garbage(&garbage); + string_list_clear(&garbage, 0); } static int sort_pack(const void *a_, const void *b_) @@ -1141,10 +1239,51 @@ static const struct packed_git *has_packed_and_bad(const unsigned char *sha1) return NULL; } -int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type) +/* + * With an in-core object data in "map", rehash it to make sure the + * object name actually matches "sha1" to detect object corruption. + * With "map" == NULL, try reading the object named with "sha1" using + * the streaming interface and rehash it to do the same. + */ +int check_sha1_signature(const unsigned char *sha1, void *map, + unsigned long size, const char *type) { unsigned char real_sha1[20]; - hash_sha1_file(map, size, type, real_sha1); + enum object_type obj_type; + struct git_istream *st; + git_SHA_CTX c; + char hdr[32]; + int hdrlen; + + if (map) { + hash_sha1_file(map, size, type, real_sha1); + return hashcmp(sha1, real_sha1) ? -1 : 0; + } + + st = open_istream(sha1, &obj_type, &size, NULL); + if (!st) + return -1; + + /* Generate the header */ + hdrlen = sprintf(hdr, "%s %lu", typename(obj_type), size) + 1; + + /* Sha1.. */ + git_SHA1_Init(&c); + git_SHA1_Update(&c, hdr, hdrlen); + for (;;) { + char buf[1024 * 16]; + ssize_t readlen = read_istream(st, buf, sizeof(buf)); + + if (readlen < 0) { + close_istream(st); + return -1; + } + if (!readlen) + break; + git_SHA1_Update(&c, buf, readlen); + } + git_SHA1_Final(real_sha1, &c); + close_istream(st); return hashcmp(sha1, real_sha1) ? -1 : 0; } @@ -1167,6 +1306,26 @@ static int git_open_noatime(const char *name) } } +static int stat_sha1_file(const unsigned char *sha1, struct stat *st) +{ + char *name = sha1_file_name(sha1); + struct alternate_object_database *alt; + + if (!lstat(name, st)) + return 0; + + prepare_alt_odb(); + errno = ENOENT; + for (alt = alt_odb_list; alt; alt = alt->next) { + name = alt->name; + fill_sha1_path(name, sha1); + if (!lstat(alt->base, st)) + return 0; + } + + return -1; +} + static int open_sha1_file(const unsigned char *sha1) { int fd; @@ -1201,6 +1360,11 @@ void *map_sha1_file(const unsigned char *sha1, unsigned long *size) if (!fstat(fd, &st)) { *size = xsize_t(st.st_size); + if (!*size) { + /* mmap() is forbidden on empty files */ + error("object file %s is empty", sha1_file_name(sha1)); + return NULL; + } map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0); } close(fd); @@ -1267,7 +1431,8 @@ unsigned long unpack_object_header_buffer(const unsigned char *buf, while (c & 0x80) { if (len <= used || bitsizeof(long) <= shift) { error("bad object header"); - return 0; + size = used = 0; + break; } c = buf[used++]; size += (c & 0x7f) << shift; @@ -1506,50 +1671,6 @@ static off_t get_delta_base(struct packed_git *p, return base_offset; } -/* forward declaration for a mutually recursive function */ -static int packed_object_info(struct packed_git *p, off_t offset, - unsigned long *sizep, int *rtype); - -static int packed_delta_info(struct packed_git *p, - struct pack_window **w_curs, - off_t curpos, - enum object_type type, - off_t obj_offset, - unsigned long *sizep) -{ - off_t base_offset; - - base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset); - if (!base_offset) - return OBJ_BAD; - type = packed_object_info(p, base_offset, NULL, NULL); - if (type <= OBJ_NONE) { - struct revindex_entry *revidx; - const unsigned char *base_sha1; - revidx = find_pack_revindex(p, base_offset); - if (!revidx) - return OBJ_BAD; - base_sha1 = nth_packed_object_sha1(p, revidx->nr); - mark_bad_packed_object(p, base_sha1); - type = sha1_object_info(base_sha1, NULL); - if (type <= OBJ_NONE) - return OBJ_BAD; - } - - /* We choose to only get the type of the base object and - * ignore potentially corrupt pack file that expects the delta - * based on a base with a wrong size. This saves tons of - * inflate() calls. - */ - if (sizep) { - *sizep = get_size_from_delta(p, w_curs, curpos); - if (*sizep == 0) - type = OBJ_BAD; - } - - return type; -} - int unpack_object_header(struct packed_git *p, struct pack_window **w_curs, off_t *curpos, @@ -1576,36 +1697,138 @@ int unpack_object_header(struct packed_git *p, return type; } -static int packed_object_info(struct packed_git *p, off_t obj_offset, - unsigned long *sizep, int *rtype) +static int retry_bad_packed_offset(struct packed_git *p, off_t obj_offset) { - struct pack_window *w_curs = NULL; - unsigned long size; - off_t curpos = obj_offset; - enum object_type type; + int type; + struct revindex_entry *revidx; + const unsigned char *sha1; + revidx = find_pack_revindex(p, obj_offset); + if (!revidx) + return OBJ_BAD; + sha1 = nth_packed_object_sha1(p, revidx->nr); + mark_bad_packed_object(p, sha1); + type = sha1_object_info(sha1, NULL); + if (type <= OBJ_NONE) + return OBJ_BAD; + return type; +} - type = unpack_object_header(p, &w_curs, &curpos, &size); - if (rtype) - *rtype = type; /* representation type */ +#define POI_STACK_PREALLOC 64 + +static enum object_type packed_to_object_type(struct packed_git *p, + off_t obj_offset, + enum object_type type, + struct pack_window **w_curs, + off_t curpos) +{ + off_t small_poi_stack[POI_STACK_PREALLOC]; + off_t *poi_stack = small_poi_stack; + int poi_stack_nr = 0, poi_stack_alloc = POI_STACK_PREALLOC; + + while (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) { + off_t base_offset; + unsigned long size; + /* Push the object we're going to leave behind */ + if (poi_stack_nr >= poi_stack_alloc && poi_stack == small_poi_stack) { + poi_stack_alloc = alloc_nr(poi_stack_nr); + poi_stack = xmalloc(sizeof(off_t)*poi_stack_alloc); + memcpy(poi_stack, small_poi_stack, sizeof(off_t)*poi_stack_nr); + } else { + ALLOC_GROW(poi_stack, poi_stack_nr+1, poi_stack_alloc); + } + poi_stack[poi_stack_nr++] = obj_offset; + /* If parsing the base offset fails, just unwind */ + base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset); + if (!base_offset) + goto unwind; + curpos = obj_offset = base_offset; + type = unpack_object_header(p, w_curs, &curpos, &size); + if (type <= OBJ_NONE) { + /* If getting the base itself fails, we first + * retry the base, otherwise unwind */ + type = retry_bad_packed_offset(p, base_offset); + if (type > OBJ_NONE) + goto out; + goto unwind; + } + } switch (type) { - case OBJ_OFS_DELTA: - case OBJ_REF_DELTA: - type = packed_delta_info(p, &w_curs, curpos, - type, obj_offset, sizep); - break; + case OBJ_BAD: case OBJ_COMMIT: case OBJ_TREE: case OBJ_BLOB: case OBJ_TAG: - if (sizep) - *sizep = size; break; default: error("unknown object type %i at offset %"PRIuMAX" in %s", type, (uintmax_t)obj_offset, p->pack_name); type = OBJ_BAD; } + +out: + if (poi_stack != small_poi_stack) + free(poi_stack); + return type; + +unwind: + while (poi_stack_nr) { + obj_offset = poi_stack[--poi_stack_nr]; + type = retry_bad_packed_offset(p, obj_offset); + if (type > OBJ_NONE) + goto out; + } + type = OBJ_BAD; + goto out; +} + +static int packed_object_info(struct packed_git *p, off_t obj_offset, + struct object_info *oi) +{ + struct pack_window *w_curs = NULL; + unsigned long size; + off_t curpos = obj_offset; + enum object_type type; + + /* + * We always get the representation type, but only convert it to + * a "real" type later if the caller is interested. + */ + type = unpack_object_header(p, &w_curs, &curpos, &size); + + if (oi->sizep) { + if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) { + off_t tmp_pos = curpos; + off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos, + type, obj_offset); + if (!base_offset) { + type = OBJ_BAD; + goto out; + } + *oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos); + if (*oi->sizep == 0) { + type = OBJ_BAD; + goto out; + } + } else { + *oi->sizep = size; + } + } + + if (oi->disk_sizep) { + struct revindex_entry *revidx = find_pack_revindex(p, obj_offset); + *oi->disk_sizep = revidx[1].offset - obj_offset; + } + + if (oi->typep) { + *oi->typep = packed_to_object_type(p, obj_offset, type, &w_curs, curpos); + if (*oi->typep < 0) { + type = OBJ_BAD; + goto out; + } + } + +out: unuse_pack(&w_curs); return type; } @@ -1669,32 +1892,51 @@ static unsigned long pack_entry_hash(struct packed_git *p, off_t base_offset) return hash % MAX_DELTA_CACHE; } -static int in_delta_base_cache(struct packed_git *p, off_t base_offset) +static struct delta_base_cache_entry * +get_delta_base_cache_entry(struct packed_git *p, off_t base_offset) { unsigned long hash = pack_entry_hash(p, base_offset); - struct delta_base_cache_entry *ent = delta_base_cache + hash; + return delta_base_cache + hash; +} + +static int eq_delta_base_cache_entry(struct delta_base_cache_entry *ent, + struct packed_git *p, off_t base_offset) +{ return (ent->data && ent->p == p && ent->base_offset == base_offset); } +static int in_delta_base_cache(struct packed_git *p, off_t base_offset) +{ + struct delta_base_cache_entry *ent; + ent = get_delta_base_cache_entry(p, base_offset); + return eq_delta_base_cache_entry(ent, p, base_offset); +} + +static void clear_delta_base_cache_entry(struct delta_base_cache_entry *ent) +{ + ent->data = NULL; + ent->lru.next->prev = ent->lru.prev; + ent->lru.prev->next = ent->lru.next; + delta_base_cached -= ent->size; +} + static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset, unsigned long *base_size, enum object_type *type, int keep_cache) { + struct delta_base_cache_entry *ent; void *ret; - unsigned long hash = pack_entry_hash(p, base_offset); - struct delta_base_cache_entry *ent = delta_base_cache + hash; - ret = ent->data; - if (!ret || ent->p != p || ent->base_offset != base_offset) + ent = get_delta_base_cache_entry(p, base_offset); + + if (!eq_delta_base_cache_entry(ent, p, base_offset)) return unpack_entry(p, base_offset, type, base_size); - if (!keep_cache) { - ent->data = NULL; - ent->lru.next->prev = ent->lru.prev; - ent->lru.prev->next = ent->lru.next; - delta_base_cached -= ent->size; - } else { + ret = ent->data; + + if (!keep_cache) + clear_delta_base_cache_entry(ent); + else ret = xmemdupz(ent->data, ent->size); - } *type = ent->type; *base_size = ent->size; return ret; @@ -1758,78 +2000,23 @@ static void add_delta_base_cache(struct packed_git *p, off_t base_offset, static void *read_object(const unsigned char *sha1, enum object_type *type, unsigned long *size); -static void *unpack_delta_entry(struct packed_git *p, - struct pack_window **w_curs, - off_t curpos, - unsigned long delta_size, - off_t obj_offset, - enum object_type *type, - unsigned long *sizep) -{ - void *delta_data, *result, *base; - unsigned long base_size; - off_t base_offset; - - base_offset = get_delta_base(p, w_curs, &curpos, *type, obj_offset); - if (!base_offset) { - error("failed to validate delta base reference " - "at offset %"PRIuMAX" from %s", - (uintmax_t)curpos, p->pack_name); - return NULL; - } - unuse_pack(w_curs); - base = cache_or_unpack_entry(p, base_offset, &base_size, type, 0); - if (!base) { - /* - * We're probably in deep shit, but let's try to fetch - * the required base anyway from another pack or loose. - * This is costly but should happen only in the presence - * of a corrupted pack, and is better than failing outright. - */ - struct revindex_entry *revidx; - const unsigned char *base_sha1; - revidx = find_pack_revindex(p, base_offset); - if (!revidx) - return NULL; - base_sha1 = nth_packed_object_sha1(p, revidx->nr); - error("failed to read delta base object %s" - " at offset %"PRIuMAX" from %s", - sha1_to_hex(base_sha1), (uintmax_t)base_offset, - p->pack_name); - mark_bad_packed_object(p, base_sha1); - base = read_object(base_sha1, type, &base_size); - if (!base) - return NULL; - } - - delta_data = unpack_compressed_entry(p, w_curs, curpos, delta_size); - if (!delta_data) { - error("failed to unpack compressed delta " - "at offset %"PRIuMAX" from %s", - (uintmax_t)curpos, p->pack_name); - free(base); - return NULL; - } - result = patch_delta(base, base_size, - delta_data, delta_size, - sizep); - if (!result) - die("failed to apply delta"); - free(delta_data); - add_delta_base_cache(p, base_offset, base, base_size, *type); - return result; -} - static void write_pack_access_log(struct packed_git *p, off_t obj_offset) { static FILE *log_file; + if (!log_pack_access) + log_pack_access = getenv("GIT_TRACE_PACK_ACCESS"); + if (!log_pack_access) + log_pack_access = no_log_pack_access; + if (log_pack_access == no_log_pack_access) + return; + if (!log_file) { log_file = fopen(log_pack_access, "w"); if (!log_file) { error("cannot open pack access log '%s' for writing: %s", log_pack_access, strerror(errno)); - log_pack_access = NULL; + log_pack_access = no_log_pack_access; return; } } @@ -1840,48 +2027,187 @@ static void write_pack_access_log(struct packed_git *p, off_t obj_offset) int do_check_packed_object_crc; +#define UNPACK_ENTRY_STACK_PREALLOC 64 +struct unpack_entry_stack_ent { + off_t obj_offset; + off_t curpos; + unsigned long size; +}; + void *unpack_entry(struct packed_git *p, off_t obj_offset, - enum object_type *type, unsigned long *sizep) + enum object_type *final_type, unsigned long *final_size) { struct pack_window *w_curs = NULL; off_t curpos = obj_offset; - void *data; + void *data = NULL; + unsigned long size; + enum object_type type; + struct unpack_entry_stack_ent small_delta_stack[UNPACK_ENTRY_STACK_PREALLOC]; + struct unpack_entry_stack_ent *delta_stack = small_delta_stack; + int delta_stack_nr = 0, delta_stack_alloc = UNPACK_ENTRY_STACK_PREALLOC; + int base_from_cache = 0; - if (log_pack_access) + if (log_pack_access != no_log_pack_access) write_pack_access_log(p, obj_offset); - if (do_check_packed_object_crc && p->index_version > 1) { - struct revindex_entry *revidx = find_pack_revindex(p, obj_offset); - unsigned long len = revidx[1].offset - obj_offset; - if (check_pack_crc(p, &w_curs, obj_offset, len, revidx->nr)) { - const unsigned char *sha1 = - nth_packed_object_sha1(p, revidx->nr); - error("bad packed object CRC for %s", - sha1_to_hex(sha1)); - mark_bad_packed_object(p, sha1); - unuse_pack(&w_curs); - return NULL; + /* PHASE 1: drill down to the innermost base object */ + for (;;) { + off_t base_offset; + int i; + struct delta_base_cache_entry *ent; + + if (do_check_packed_object_crc && p->index_version > 1) { + struct revindex_entry *revidx = find_pack_revindex(p, obj_offset); + unsigned long len = revidx[1].offset - obj_offset; + if (check_pack_crc(p, &w_curs, obj_offset, len, revidx->nr)) { + const unsigned char *sha1 = + nth_packed_object_sha1(p, revidx->nr); + error("bad packed object CRC for %s", + sha1_to_hex(sha1)); + mark_bad_packed_object(p, sha1); + unuse_pack(&w_curs); + return NULL; + } + } + + ent = get_delta_base_cache_entry(p, curpos); + if (eq_delta_base_cache_entry(ent, p, curpos)) { + type = ent->type; + data = ent->data; + size = ent->size; + clear_delta_base_cache_entry(ent); + base_from_cache = 1; + break; } + + type = unpack_object_header(p, &w_curs, &curpos, &size); + if (type != OBJ_OFS_DELTA && type != OBJ_REF_DELTA) + break; + + base_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset); + if (!base_offset) { + error("failed to validate delta base reference " + "at offset %"PRIuMAX" from %s", + (uintmax_t)curpos, p->pack_name); + /* bail to phase 2, in hopes of recovery */ + data = NULL; + break; + } + + /* push object, proceed to base */ + if (delta_stack_nr >= delta_stack_alloc + && delta_stack == small_delta_stack) { + delta_stack_alloc = alloc_nr(delta_stack_nr); + delta_stack = xmalloc(sizeof(*delta_stack)*delta_stack_alloc); + memcpy(delta_stack, small_delta_stack, + sizeof(*delta_stack)*delta_stack_nr); + } else { + ALLOC_GROW(delta_stack, delta_stack_nr+1, delta_stack_alloc); + } + i = delta_stack_nr++; + delta_stack[i].obj_offset = obj_offset; + delta_stack[i].curpos = curpos; + delta_stack[i].size = size; + + curpos = obj_offset = base_offset; } - *type = unpack_object_header(p, &w_curs, &curpos, sizep); - switch (*type) { + /* PHASE 2: handle the base */ + switch (type) { case OBJ_OFS_DELTA: case OBJ_REF_DELTA: - data = unpack_delta_entry(p, &w_curs, curpos, *sizep, - obj_offset, type, sizep); + if (data) + die("BUG in unpack_entry: left loop at a valid delta"); break; case OBJ_COMMIT: case OBJ_TREE: case OBJ_BLOB: case OBJ_TAG: - data = unpack_compressed_entry(p, &w_curs, curpos, *sizep); + if (!base_from_cache) + data = unpack_compressed_entry(p, &w_curs, curpos, size); break; default: data = NULL; error("unknown object type %i at offset %"PRIuMAX" in %s", - *type, (uintmax_t)obj_offset, p->pack_name); + type, (uintmax_t)obj_offset, p->pack_name); } + + /* PHASE 3: apply deltas in order */ + + /* invariants: + * 'data' holds the base data, or NULL if there was corruption + */ + while (delta_stack_nr) { + void *delta_data; + void *base = data; + unsigned long delta_size, base_size = size; + int i; + + data = NULL; + + if (base) + add_delta_base_cache(p, obj_offset, base, base_size, type); + + if (!base) { + /* + * We're probably in deep shit, but let's try to fetch + * the required base anyway from another pack or loose. + * This is costly but should happen only in the presence + * of a corrupted pack, and is better than failing outright. + */ + struct revindex_entry *revidx; + const unsigned char *base_sha1; + revidx = find_pack_revindex(p, obj_offset); + if (revidx) { + base_sha1 = nth_packed_object_sha1(p, revidx->nr); + error("failed to read delta base object %s" + " at offset %"PRIuMAX" from %s", + sha1_to_hex(base_sha1), (uintmax_t)obj_offset, + p->pack_name); + mark_bad_packed_object(p, base_sha1); + base = read_object(base_sha1, &type, &base_size); + } + } + + i = --delta_stack_nr; + obj_offset = delta_stack[i].obj_offset; + curpos = delta_stack[i].curpos; + delta_size = delta_stack[i].size; + + if (!base) + continue; + + delta_data = unpack_compressed_entry(p, &w_curs, curpos, delta_size); + + if (!delta_data) { + error("failed to unpack compressed delta " + "at offset %"PRIuMAX" from %s", + (uintmax_t)curpos, p->pack_name); + data = NULL; + continue; + } + + data = patch_delta(base, base_size, + delta_data, delta_size, + &size); + + /* + * We could not apply the delta; warn the user, but keep going. + * Our failure will be noticed either in the next iteration of + * the loop, or if this is the final delta, in the caller when + * we return NULL. Those code paths will take care of making + * a more explicit warning and retrying with another copy of + * the object. + */ + if (!data) + error("failed to apply delta"); + + free(delta_data); + } + + *final_type = type; + *final_size = size; + unuse_pack(&w_curs); return data; } @@ -2008,54 +2334,58 @@ int is_pack_valid(struct packed_git *p) return !open_packed_git(p); } +static int fill_pack_entry(const unsigned char *sha1, + struct pack_entry *e, + struct packed_git *p) +{ + off_t offset; + + if (p->num_bad_objects) { + unsigned i; + for (i = 0; i < p->num_bad_objects; i++) + if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) + return 0; + } + + offset = find_pack_entry_one(sha1, p); + if (!offset) + return 0; + + /* + * We are about to tell the caller where they can locate the + * requested object. We better make sure the packfile is + * still here and can be accessed before supplying that + * answer, as it may have been deleted since the index was + * loaded! + */ + if (!is_pack_valid(p)) { + warning("packfile %s cannot be accessed", p->pack_name); + return 0; + } + e->offset = offset; + e->p = p; + hashcpy(e->sha1, sha1); + return 1; +} + static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e) { - static struct packed_git *last_found = (void *)1; struct packed_git *p; - off_t offset; prepare_packed_git(); if (!packed_git) return 0; - p = (last_found == (void *)1) ? packed_git : last_found; - do { - if (p->num_bad_objects) { - unsigned i; - for (i = 0; i < p->num_bad_objects; i++) - if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) - goto next; - } + if (last_found_pack && fill_pack_entry(sha1, e, last_found_pack)) + return 1; - offset = find_pack_entry_one(sha1, p); - if (offset) { - /* - * We are about to tell the caller where they can - * locate the requested object. We better make - * sure the packfile is still here and can be - * accessed before supplying that answer, as - * it may have been deleted since the index - * was loaded! - */ - if (!is_pack_valid(p)) { - warning("packfile %s cannot be accessed", p->pack_name); - goto next; - } - e->offset = offset; - e->p = p; - hashcpy(e->sha1, sha1); - last_found = p; - return 1; - } + for (p = packed_git; p; p = p->next) { + if (p == last_found_pack || !fill_pack_entry(sha1, e, p)) + continue; - next: - if (p == last_found) - p = packed_git; - else - p = p->next; - if (p == last_found) - p = p->next; - } while (p); + last_found_pack = p; + return 1; + } return 0; } @@ -2072,7 +2402,8 @@ struct packed_git *find_sha1_pack(const unsigned char *sha1, } -static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *sizep) +static int sha1_loose_object_info(const unsigned char *sha1, + struct object_info *oi) { int status; unsigned long mapsize, size; @@ -2080,19 +2411,37 @@ static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *size git_zstream stream; char hdr[32]; + /* + * If we don't care about type or size, then we don't + * need to look inside the object at all. + */ + if (!oi->typep && !oi->sizep) { + if (oi->disk_sizep) { + struct stat st; + if (stat_sha1_file(sha1, &st) < 0) + return -1; + *oi->disk_sizep = st.st_size; + } + return 0; + } + map = map_sha1_file(sha1, &mapsize); if (!map) - return error("unable to find %s", sha1_to_hex(sha1)); + return -1; + if (oi->disk_sizep) + *oi->disk_sizep = mapsize; if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0) status = error("unable to unpack %s header", sha1_to_hex(sha1)); else if ((status = parse_sha1_header(hdr, &size)) < 0) status = error("unable to parse %s header", sha1_to_hex(sha1)); - else if (sizep) - *sizep = size; + else if (oi->sizep) + *oi->sizep = size; git_inflate_end(&stream); munmap(map, mapsize); - return status; + if (oi->typep) + *oi->typep = status; + return 0; } /* returns enum object_type or negative */ @@ -2100,34 +2449,37 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi) { struct cached_object *co; struct pack_entry e; - int status, rtype; + int rtype; co = find_cached_object(sha1); if (co) { + if (oi->typep) + *(oi->typep) = co->type; if (oi->sizep) *(oi->sizep) = co->size; + if (oi->disk_sizep) + *(oi->disk_sizep) = 0; oi->whence = OI_CACHED; - return co->type; + return 0; } if (!find_pack_entry(sha1, &e)) { /* Most likely it's a loose object. */ - status = sha1_loose_object_info(sha1, oi->sizep); - if (status >= 0) { + if (!sha1_loose_object_info(sha1, oi)) { oi->whence = OI_LOOSE; - return status; + return 0; } /* Not a loose object; someone else may have just packed it. */ reprepare_packed_git(); if (!find_pack_entry(sha1, &e)) - return status; + return -1; } - status = packed_object_info(e.p, e.offset, oi->sizep, &rtype); - if (status < 0) { + rtype = packed_object_info(e.p, e.offset, oi); + if (rtype < 0) { mark_bad_packed_object(e.p, sha1); - status = sha1_object_info_extended(sha1, oi); + return sha1_object_info_extended(sha1, oi); } else if (in_delta_base_cache(e.p, e.offset)) { oi->whence = OI_DBCACHED; } else { @@ -2138,15 +2490,19 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi) rtype == OBJ_OFS_DELTA); } - return status; + return 0; } int sha1_object_info(const unsigned char *sha1, unsigned long *sizep) { - struct object_info oi; + enum object_type type; + struct object_info oi = {NULL}; + oi.typep = &type; oi.sizep = sizep; - return sha1_object_info_extended(sha1, &oi); + if (sha1_object_info_extended(sha1, &oi) < 0) + return -1; + return type; } static void *read_packed_sha1(const unsigned char *sha1, @@ -2364,7 +2720,7 @@ int move_temp_to_file(const char *tmpfile, const char *filename) unlink_or_warn(tmpfile); if (ret) { if (ret != EEXIST) { - return error("unable to write sha1 filename %s: %s\n", filename, strerror(ret)); + return error("unable to write sha1 filename %s: %s", filename, strerror(ret)); } /* FIXME!!! Collision check here ? */ } @@ -2450,15 +2806,15 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen, git_SHA_CTX c; unsigned char parano_sha1[20]; char *filename; - static char tmpfile[PATH_MAX]; + static char tmp_file[PATH_MAX]; filename = sha1_file_name(sha1); - fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename); + fd = create_tmpfile(tmp_file, sizeof(tmp_file), filename); if (fd < 0) { if (errno == EACCES) - return error("insufficient permission for adding an object to repository database %s\n", get_object_directory()); + return error("insufficient permission for adding an object to repository database %s", get_object_directory()); else - return error("unable to create temporary sha1 filename %s: %s\n", tmpfile, strerror(errno)); + return error("unable to create temporary file: %s", strerror(errno)); } /* Set it up */ @@ -2503,12 +2859,12 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen, struct utimbuf utb; utb.actime = mtime; utb.modtime = mtime; - if (utime(tmpfile, &utb) < 0) + if (utime(tmp_file, &utb) < 0) warning("failed utime() on %s: %s", - tmpfile, strerror(errno)); + tmp_file, strerror(errno)); } - return move_temp_to_file(tmpfile, filename); + return move_temp_to_file(tmp_file, filename); } int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *returnsha1) @@ -2679,82 +3035,25 @@ static int index_core(unsigned char *sha1, int fd, size_t size, } /* - * This creates one packfile per large blob, because the caller - * immediately wants the result sha1, and fast-import can report the - * object name via marks mechanism only by closing the created - * packfile. + * This creates one packfile per large blob unless bulk-checkin + * machinery is "plugged". * * This also bypasses the usual "convert-to-git" dance, and that is on * purpose. We could write a streaming version of the converting * functions and insert that before feeding the data to fast-import - * (or equivalent in-core API described above), but the primary - * motivation for trying to stream from the working tree file and to - * avoid mmaping it in core is to deal with large binary blobs, and - * by definition they do _not_ want to get any conversion. + * (or equivalent in-core API described above). However, that is + * somewhat complicated, as we do not know the size of the filter + * result, which we need to know beforehand when writing a git object. + * Since the primary motivation for trying to stream from the working + * tree file and to avoid mmaping it in core is to deal with large + * binary blobs, they generally do not want to get any conversion, and + * callers should avoid this code path when filters are requested. */ static int index_stream(unsigned char *sha1, int fd, size_t size, enum object_type type, const char *path, unsigned flags) { - struct child_process fast_import; - char export_marks[512]; - const char *argv[] = { "fast-import", "--quiet", export_marks, NULL }; - char tmpfile[512]; - char fast_import_cmd[512]; - char buf[512]; - int len, tmpfd; - - strcpy(tmpfile, git_path("hashstream_XXXXXX")); - tmpfd = git_mkstemp_mode(tmpfile, 0600); - if (tmpfd < 0) - die_errno("cannot create tempfile: %s", tmpfile); - if (close(tmpfd)) - die_errno("cannot close tempfile: %s", tmpfile); - sprintf(export_marks, "--export-marks=%s", tmpfile); - - memset(&fast_import, 0, sizeof(fast_import)); - fast_import.in = -1; - fast_import.argv = argv; - fast_import.git_cmd = 1; - if (start_command(&fast_import)) - die_errno("index-stream: git fast-import failed"); - - len = sprintf(fast_import_cmd, "blob\nmark :1\ndata %lu\n", - (unsigned long) size); - write_or_whine(fast_import.in, fast_import_cmd, len, - "index-stream: feeding fast-import"); - while (size) { - char buf[10240]; - size_t sz = size < sizeof(buf) ? size : sizeof(buf); - ssize_t actual; - - actual = read_in_full(fd, buf, sz); - if (actual < 0) - die_errno("index-stream: reading input"); - if (write_in_full(fast_import.in, buf, actual) != actual) - die_errno("index-stream: feeding fast-import"); - size -= actual; - } - if (close(fast_import.in)) - die_errno("index-stream: closing fast-import"); - if (finish_command(&fast_import)) - die_errno("index-stream: finishing fast-import"); - - tmpfd = open(tmpfile, O_RDONLY); - if (tmpfd < 0) - die_errno("index-stream: cannot open fast-import mark"); - len = read(tmpfd, buf, sizeof(buf)); - if (len < 0) - die_errno("index-stream: reading fast-import mark"); - if (close(tmpfd) < 0) - die_errno("index-stream: closing fast-import mark"); - if (unlink(tmpfile)) - die_errno("index-stream: unlinking fast-import mark"); - if (len != 44 || - memcmp(":1 ", buf, 3) || - get_sha1_hex(buf + 3, sha1)) - die_errno("index-stream: unexpected fast-import mark: <%s>", buf); - return 0; + return index_bulk_checkin(sha1, fd, size, type, path, flags); } int index_fd(unsigned char *sha1, int fd, struct stat *st, @@ -2765,7 +3064,8 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, if (!S_ISREG(st->st_mode)) ret = index_pipe(sha1, fd, type, path, flags); - else if (size <= big_file_threshold || type != OBJ_BLOB) + else if (size <= big_file_threshold || type != OBJ_BLOB || + (path && would_convert_to_git(path, NULL, 0, 0))) ret = index_core(sha1, fd, size, type, path, flags); else ret = index_stream(sha1, fd, size, type, path, flags); |