diff options
Diffstat (limited to 'sha1_file.c')
| -rw-r--r-- | sha1_file.c | 735 |
1 files changed, 425 insertions, 310 deletions
diff --git a/sha1_file.c b/sha1_file.c index bcfcab351d..e194f6a128 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -35,59 +35,41 @@ static size_t sz_fmt(size_t s) { return s; } const unsigned char null_sha1[20]; -const signed char hexval_table[256] = { - -1, -1, -1, -1, -1, -1, -1, -1, /* 00-07 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 08-0f */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 10-17 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 18-1f */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 20-27 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 28-2f */ - 0, 1, 2, 3, 4, 5, 6, 7, /* 30-37 */ - 8, 9, -1, -1, -1, -1, -1, -1, /* 38-3f */ - -1, 10, 11, 12, 13, 14, 15, -1, /* 40-47 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 48-4f */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 50-57 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 58-5f */ - -1, 10, 11, 12, 13, 14, 15, -1, /* 60-67 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 68-67 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 70-77 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 78-7f */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 80-87 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 88-8f */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 90-97 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* 98-9f */ - -1, -1, -1, -1, -1, -1, -1, -1, /* a0-a7 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* a8-af */ - -1, -1, -1, -1, -1, -1, -1, -1, /* b0-b7 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* b8-bf */ - -1, -1, -1, -1, -1, -1, -1, -1, /* c0-c7 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* c8-cf */ - -1, -1, -1, -1, -1, -1, -1, -1, /* d0-d7 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* d8-df */ - -1, -1, -1, -1, -1, -1, -1, -1, /* e0-e7 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* e8-ef */ - -1, -1, -1, -1, -1, -1, -1, -1, /* f0-f7 */ - -1, -1, -1, -1, -1, -1, -1, -1, /* f8-ff */ +static int git_open_noatime(const char *name, struct packed_git *p); + +/* + * 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 + * to write them into the object store (e.g. a browse-only + * application). + */ +static struct cached_object { + unsigned char sha1[20]; + enum object_type type; + void *buf; + unsigned long size; +} *cached_objects; +static int cached_object_nr, cached_object_alloc; + +static struct cached_object empty_tree = { + EMPTY_TREE_SHA1_BIN_LITERAL, + OBJ_TREE, + "", + 0 }; -int get_sha1_hex(const char *hex, unsigned char *sha1) +static struct cached_object *find_cached_object(const unsigned char *sha1) { int i; - for (i = 0; i < 20; i++) { - unsigned int val = (hexval(hex[0]) << 4) | hexval(hex[1]); - if (val & ~0xff) - return -1; - *sha1++ = val; - hex += 2; - } - return 0; -} + struct cached_object *co = cached_objects; -static inline int offset_1st_component(const char *path) -{ - if (has_dos_drive_prefix(path)) - return 2 + (path[2] == '/'); - return *path == '/'; + for (i = 0; i < cached_object_nr; i++, co++) { + if (!hashcmp(co->sha1, sha1)) + return co; + } + if (!hashcmp(sha1, empty_tree.sha1)) + return &empty_tree; + return NULL; } int safe_create_leading_directories(char *path) @@ -99,7 +81,11 @@ int safe_create_leading_directories(char *path) pos = strchr(pos, '/'); if (!pos) break; - *pos = 0; + while (*++pos == '/') + ; + if (!*pos) + break; + *--pos = '\0'; if (!stat(path, &st)) { /* path exists */ if (!S_ISDIR(st.st_mode)) { @@ -129,24 +115,6 @@ int safe_create_leading_directories_const(const char *path) return result; } -char *sha1_to_hex(const unsigned char *sha1) -{ - static int bufno; - static char hexbuffer[4][50]; - static const char hex[] = "0123456789abcdef"; - char *buffer = hexbuffer[3 & ++bufno], *buf = buffer; - int i; - - for (i = 0; i < 20; i++) { - unsigned int val = *sha1++; - *buf++ = hex[val >> 4]; - *buf++ = hex[val & 0xf]; - } - *buf = '\0'; - - return buffer; -} - static void fill_sha1_path(char *pathbuf, const unsigned char *sha1) { int i; @@ -171,20 +139,22 @@ static void fill_sha1_path(char *pathbuf, const unsigned char *sha1) */ char *sha1_file_name(const unsigned char *sha1) { - static char *name, *base; + static char buf[PATH_MAX]; + const char *objdir; + int len; - if (!base) { - const char *sha1_file_directory = get_object_directory(); - int len = strlen(sha1_file_directory); - base = xmalloc(len + 60); - memcpy(base, sha1_file_directory, len); - memset(base+len, 0, 60); - base[len] = '/'; - base[len+3] = '/'; - name = base + len + 1; - } - fill_sha1_path(name, sha1); - return base; + objdir = get_object_directory(); + len = strlen(objdir); + + /* '/' + sha1(2) + '/' + sha1(38) + '\0' */ + if (len + 43 > PATH_MAX) + die("insanely long object directory %s", objdir); + memcpy(buf, objdir, len); + buf[len] = '/'; + buf[len+3] = '/'; + buf[len+42] = '\0'; + fill_sha1_path(buf + len + 1, sha1); + return buf; } static char *sha1_get_pack_name(const unsigned char *sha1, @@ -250,7 +220,6 @@ static void read_info_alternates(const char * alternates, int depth); */ static int link_alt_odb_entry(const char * entry, int len, const char * relative_base, int depth) { - struct stat st; const char *objdir = get_object_directory(); struct alternate_object_database *ent; struct alternate_object_database *alt; @@ -281,7 +250,7 @@ static int link_alt_odb_entry(const char * entry, int len, const char * relative ent->base[pfxlen] = ent->base[entlen-1] = 0; /* Detect cases where alternate disappeared */ - if (stat(ent->base, &st) || !S_ISDIR(st.st_mode)) { + if (!is_directory(ent->base)) { error("object directory %s does not exist; " "check .git/objects/info/alternates.", ent->base); @@ -366,7 +335,7 @@ static void read_info_alternates(const char * relative_base, int depth) int fd; sprintf(path, "%s/%s", relative_base, alt_file_name); - fd = open(path, O_RDONLY); + fd = git_open_noatime(path, NULL); if (fd < 0) return; if (fstat(fd, &st) || (st.st_size == 0)) { @@ -394,6 +363,16 @@ void add_to_alternates_file(const char *reference) link_alt_odb_entries(alt, alt + strlen(alt), '\n', NULL, 0); } +void foreach_alt_odb(alt_odb_fn fn, void *cb) +{ + struct alternate_object_database *ent; + + prepare_alt_odb(); + for (ent = alt_odb_list; ent; ent = ent->next) + if (fn(ent, cb)) + return; +} + void prepare_alt_odb(void) { const char *alt; @@ -438,6 +417,8 @@ static unsigned int pack_used_ctr; static unsigned int pack_mmap_calls; static unsigned int peak_pack_open_windows; static unsigned int pack_open_windows; +static unsigned int pack_open_fds; +static unsigned int pack_max_fds; static size_t peak_pack_mapped; static size_t pack_mapped; struct packed_git *packed_git; @@ -469,7 +450,7 @@ static int check_packed_git_idx(const char *path, struct packed_git *p) struct pack_idx_header *hdr; size_t idx_size; uint32_t version, nr, i, *index; - int fd = open(path, O_RDONLY); + int fd = git_open_noatime(path, p); struct stat st; if (fd < 0) @@ -615,8 +596,10 @@ static int unuse_one_window(struct packed_git *current, int keep_fd) lru_l->next = lru_w->next; else { lru_p->windows = lru_w->next; - if (!lru_p->windows && lru_p->pack_fd != keep_fd) { + if (!lru_p->windows && lru_p->pack_fd != -1 + && lru_p->pack_fd != keep_fd) { close(lru_p->pack_fd); + pack_open_fds--; lru_p->pack_fd = -1; } } @@ -634,6 +617,21 @@ void release_pack_memory(size_t need, int fd) ; /* nothing */ } +void *xmmap(void *start, size_t length, + int prot, int flags, int fd, off_t offset) +{ + void *ret = mmap(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) { + if (!length) + return NULL; + release_pack_memory(length, fd); + ret = mmap(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) + die_errno("Out of memory? mmap failed"); + } + return ret; +} + void close_pack_windows(struct packed_git *p) { while (p->windows) { @@ -659,6 +657,14 @@ void unuse_pack(struct pack_window **w_cursor) } } +void close_pack_index(struct packed_git *p) +{ + if (p->index_data) { + munmap((void *)p->index_data, p->index_size); + p->index_data = NULL; + } +} + /* * This is used by git-repack in case a newly created pack happens to * contain the same set of objects as an existing one. In that case @@ -678,10 +684,11 @@ void free_pack_by_name(const char *pack_name) if (strcmp(pack_name, p->pack_name) == 0) { clear_delta_base_cache(); close_pack_windows(p); - if (p->pack_fd != -1) + if (p->pack_fd != -1) { close(p->pack_fd); - if (p->index_data) - munmap((void *)p->index_data, p->index_size); + pack_open_fds--; + } + close_pack_index(p); free(p->bad_object_sha1); *pp = p->next; free(p); @@ -706,9 +713,29 @@ static int open_packed_git_1(struct packed_git *p) if (!p->index_data && open_pack_index(p)) return error("packfile %s index unavailable", p->pack_name); - p->pack_fd = open(p->pack_name, O_RDONLY); + 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; + + /* Save 3 for stdin/stdout/stderr, 22 for work */ + if (25 < max_fds) + pack_max_fds = max_fds - 25; + else + pack_max_fds = 1; + } + + while (pack_max_fds <= pack_open_fds && unuse_one_window(NULL, -1)) + ; /* nothing */ + + p->pack_fd = git_open_noatime(p->pack_name, p); if (p->pack_fd < 0 || fstat(p->pack_fd, &st)) return -1; + pack_open_fds++; /* If we created the struct before we had the pack we lack size. */ if (!p->pack_size) { @@ -760,6 +787,7 @@ static int open_packed_git(struct packed_git *p) return 0; if (p->pack_fd != -1) { close(p->pack_fd); + pack_open_fds--; p->pack_fd = -1; } return -1; @@ -778,21 +806,20 @@ static int in_window(struct pack_window *win, off_t offset) && (offset + 20) <= (win_off + win->len); } -unsigned char* use_pack(struct packed_git *p, +unsigned char *use_pack(struct packed_git *p, struct pack_window **w_cursor, off_t offset, unsigned int *left) { struct pack_window *win = *w_cursor; - if (p->pack_fd == -1 && open_packed_git(p)) - die("packfile %s cannot be accessed", p->pack_name); - - /* Since packfiles end in a hash of their content and its + /* Since packfiles end in a hash of their content and it's * pointless to ask for an offset into the middle of that * hash, and the in_window function above wouldn't match * don't allow an offset too close to the end of the file. */ + if (!p->pack_size && p->pack_fd == -1 && open_packed_git(p)) + die("packfile %s cannot be accessed", p->pack_name); if (offset > (p->pack_size - 20)) die("offset beyond end of packfile (truncated pack?)"); @@ -806,6 +833,10 @@ unsigned char* use_pack(struct packed_git *p, if (!win) { size_t window_align = packed_git_window_size / 2; off_t len; + + if (p->pack_fd == -1 && open_packed_git(p)) + die("packfile %s cannot be accessed", p->pack_name); + win = xcalloc(1, sizeof(*win)); win->offset = (offset / window_align) * window_align; len = p->pack_size - win->offset; @@ -823,6 +854,12 @@ unsigned char* use_pack(struct packed_git *p, die("packfile %s cannot be mapped: %s", p->pack_name, strerror(errno)); + if (!win->offset && win->len == p->pack_size + && !p->do_not_close) { + close(p->pack_fd); + pack_open_fds--; + p->pack_fd = -1; + } pack_mmap_calls++; pack_open_windows++; if (pack_mapped > peak_pack_mapped) @@ -852,11 +889,22 @@ static struct packed_git *alloc_packed_git(int extra) return p; } +static void try_to_free_pack_memory(size_t size) +{ + release_pack_memory(size, -1); +} + struct packed_git *add_packed_git(const char *path, int path_len, int local) { + static int have_set_try_to_free_routine; struct stat st; struct packed_git *p = alloc_packed_git(path_len + 2); + if (!have_set_try_to_free_routine) { + have_set_try_to_free_routine = 1; + set_try_to_free_routine(try_to_free_pack_memory); + } + /* * Make sure a corresponding .pack file exists and that * the index looks sane. @@ -889,9 +937,8 @@ struct packed_git *add_packed_git(const char *path, int path_len, int local) return p; } -struct packed_git *parse_pack_index(unsigned char *sha1) +struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path) { - const char *idx_path = sha1_pack_index_name(sha1); const char *path = sha1_pack_name(sha1); struct packed_git *p = alloc_packed_git(strlen(path) + 1); @@ -907,6 +954,9 @@ struct packed_git *parse_pack_index(unsigned char *sha1) void install_packed_git(struct packed_git *pack) { + if (pack->pack_fd != -1) + pack_open_fds++; + pack->next = packed_git; packed_git = pack; } @@ -1051,7 +1101,7 @@ static void mark_bad_packed_object(struct packed_git *p, p->num_bad_objects++; } -static int has_packed_and_bad(const unsigned char *sha1) +static const struct packed_git *has_packed_and_bad(const unsigned char *sha1) { struct packed_git *p; unsigned i; @@ -1059,8 +1109,8 @@ static int has_packed_and_bad(const unsigned char *sha1) for (p = packed_git; p; p = p->next) for (i = 0; i < p->num_bad_objects; i++) if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) - return 1; - return 0; + return p; + return NULL; } int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type) @@ -1070,18 +1120,23 @@ int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long siz return hashcmp(sha1, real_sha1) ? -1 : 0; } -static int git_open_noatime(const char *name) +static int git_open_noatime(const char *name, struct packed_git *p) { static int sha1_file_open_flag = O_NOATIME; - int fd = open(name, O_RDONLY | sha1_file_open_flag); - /* Might the failure be due to O_NOATIME? */ - if (fd < 0 && errno != ENOENT && sha1_file_open_flag) { - fd = open(name, O_RDONLY); + for (;;) { + int fd = open(name, O_RDONLY | sha1_file_open_flag); if (fd >= 0) + return fd; + + /* Might the failure be due to O_NOATIME? */ + if (errno != ENOENT && sha1_file_open_flag) { sha1_file_open_flag = 0; + continue; + } + + return -1; } - return fd; } static int open_sha1_file(const unsigned char *sha1) @@ -1090,7 +1145,7 @@ static int open_sha1_file(const unsigned char *sha1) char *name = sha1_file_name(sha1); struct alternate_object_database *alt; - fd = git_open_noatime(name); + fd = git_open_noatime(name, NULL); if (fd >= 0) return fd; @@ -1099,7 +1154,7 @@ static int open_sha1_file(const unsigned char *sha1) for (alt = alt_odb_list; alt; alt = alt->next) { name = alt->name; fill_sha1_path(name, sha1); - fd = git_open_noatime(alt->base); + fd = git_open_noatime(alt->base, NULL); if (fd >= 0) return fd; } @@ -1141,11 +1196,11 @@ static int legacy_loose_object(unsigned char *map) return 0; } -unsigned long unpack_object_header_gently(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep) +unsigned long unpack_object_header_buffer(const unsigned char *buf, + unsigned long len, enum object_type *type, unsigned long *sizep) { unsigned shift; - unsigned char c; - unsigned long size; + unsigned long size, c; unsigned long used = 0; c = buf[used++]; @@ -1153,10 +1208,10 @@ unsigned long unpack_object_header_gently(const unsigned char *buf, unsigned lon size = c & 15; shift = 4; while (c & 0x80) { - if (len <= used) - return 0; - if (sizeof(long) * 8 <= shift) + if (len <= used || bitsizeof(long) <= shift) { + error("bad object header"); return 0; + } c = buf[used++]; size += (c & 0x7f) << shift; shift += 7; @@ -1183,8 +1238,8 @@ static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned lon stream->avail_out = bufsiz; if (legacy_loose_object(map)) { - inflateInit(stream); - return inflate(stream, 0); + git_inflate_init(stream); + return git_inflate(stream, 0); } @@ -1195,7 +1250,7 @@ static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned lon * really worth it and we don't write it any longer. But we * can still read it. */ - used = unpack_object_header_gently(map, mapsize, &type, &size); + used = unpack_object_header_buffer(map, mapsize, &type, &size); if (!used || !valid_loose_object_type[type]) return -1; map += used; @@ -1204,7 +1259,7 @@ static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned lon /* Set up the stream for the rest.. */ stream->next_in = map; stream->avail_in = mapsize; - inflateInit(stream); + git_inflate_init(stream); /* And generate the fake traditional header */ stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu", @@ -1215,7 +1270,7 @@ static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned lon static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size, const unsigned char *sha1) { int bytes = strlen(buffer) + 1; - unsigned char *buf = xmalloc(1+size); + unsigned char *buf = xmallocz(size); unsigned long n; int status = Z_OK; @@ -1241,11 +1296,10 @@ static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size stream->next_out = buf + bytes; stream->avail_out = size - bytes; while (status == Z_OK) - status = inflate(stream, Z_FINISH); + status = git_inflate(stream, Z_FINISH); } - buf[size] = 0; if (status == Z_STREAM_END && !stream->avail_in) { - inflateEnd(stream); + git_inflate_end(stream); return buf; } @@ -1335,17 +1389,19 @@ unsigned long get_size_from_delta(struct packed_git *p, stream.next_out = delta_head; stream.avail_out = sizeof(delta_head); - inflateInit(&stream); + git_inflate_init(&stream); do { in = use_pack(p, w_curs, curpos, &stream.avail_in); stream.next_in = in; - st = inflate(&stream, Z_FINISH); + st = git_inflate(&stream, Z_FINISH); curpos += stream.next_in - in; } while ((st == Z_OK || st == Z_BUF_ERROR) && stream.total_out < sizeof(delta_head)); - inflateEnd(&stream); - if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) - die("delta data unpack-initial failed"); + git_inflate_end(&stream); + if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) { + error("delta data unpack-initial failed"); + return 0; + } /* Examine the initial part of the delta to figure out * the result size. @@ -1386,7 +1442,7 @@ static off_t get_delta_base(struct packed_git *p, base_offset = (base_offset << 7) + (c & 127); } base_offset = delta_obj_offset - base_offset; - if (base_offset >= delta_obj_offset) + if (base_offset <= 0 || base_offset >= delta_obj_offset) return 0; /* out of bound */ *curpos += used; } else if (type == OBJ_REF_DELTA) { @@ -1412,15 +1468,32 @@ static int packed_delta_info(struct packed_git *p, 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); + 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) + if (sizep) { *sizep = get_size_from_delta(p, w_curs, curpos); + if (*sizep == 0) + type = OBJ_BAD; + } return type; } @@ -1442,10 +1515,11 @@ static int unpack_object_header(struct packed_git *p, * insane, so we know won't exceed what we have been given. */ base = use_pack(p, w_curs, *curpos, &left); - used = unpack_object_header_gently(base, left, &type, sizep); - if (!used) - die("object offset outside of pack file"); - *curpos += used; + used = unpack_object_header_buffer(base, left, &type, sizep); + if (!used) { + type = OBJ_BAD; + } else + *curpos += used; return type; } @@ -1529,8 +1603,9 @@ static int packed_object_info(struct packed_git *p, off_t obj_offset, *sizep = size; break; default: - die("pack %s contains unknown object type %d", - p->pack_name, type); + error("unknown object type %i at offset %"PRIuMAX" in %s", + type, (uintmax_t)obj_offset, p->pack_name); + type = OBJ_BAD; } unuse_pack(&w_curs); return type; @@ -1545,20 +1620,21 @@ static void *unpack_compressed_entry(struct packed_git *p, z_stream stream; unsigned char *buffer, *in; - buffer = xmalloc(size + 1); - buffer[size] = 0; + buffer = xmallocz(size); memset(&stream, 0, sizeof(stream)); stream.next_out = buffer; - stream.avail_out = size; + stream.avail_out = size + 1; - inflateInit(&stream); + git_inflate_init(&stream); do { in = use_pack(p, w_curs, curpos, &stream.avail_in); stream.next_in = in; - st = inflate(&stream, Z_FINISH); + st = git_inflate(&stream, Z_FINISH); + if (!stream.avail_out) + break; /* the payload is larger than it should be */ curpos += stream.next_in - in; } while (st == Z_OK || st == Z_BUF_ERROR); - inflateEnd(&stream); + git_inflate_end(&stream); if ((st != Z_STREAM_END) || stream.total_out != size) { free(buffer); return NULL; @@ -1602,11 +1678,9 @@ static void *cache_or_unpack_entry(struct packed_git *p, off_t 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) - goto found_cache_entry; - return unpack_entry(p, base_offset, type, base_size); + if (!ret || ent->p != p || ent->base_offset != base_offset) + return unpack_entry(p, base_offset, type, base_size); -found_cache_entry: if (!keep_cache) { ent->data = NULL; ent->lru.next->prev = ent->lru.prev; @@ -1675,6 +1749,9 @@ static void add_delta_base_cache(struct packed_git *p, off_t base_offset, delta_base_cache_lru.prev = &ent->lru; } +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, @@ -1703,9 +1780,12 @@ static void *unpack_delta_entry(struct packed_git *p, * This is costly but should happen only in the presence * of a corrupted pack, and is better than failing outright. */ - struct revindex_entry *revidx = find_pack_revindex(p, base_offset); - const unsigned char *base_sha1 = - nth_packed_object_sha1(p, revidx->nr); + 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, @@ -1734,6 +1814,8 @@ static void *unpack_delta_entry(struct packed_git *p, return result; } +int do_check_packed_object_crc; + void *unpack_entry(struct packed_git *p, off_t obj_offset, enum object_type *type, unsigned long *sizep) { @@ -1741,6 +1823,20 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset, off_t curpos = obj_offset; void *data; + 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; + } + } + *type = unpack_object_header(p, &w_curs, &curpos, sizep); switch (*type) { case OBJ_OFS_DELTA: @@ -1864,25 +1960,28 @@ off_t find_pack_entry_one(const unsigned char *sha1, return 0; } -int matches_pack_name(struct packed_git *p, const char *name) +static int is_pack_valid(struct packed_git *p) { - const char *last_c, *c; - - if (!strcmp(p->pack_name, name)) + /* An already open pack is known to be valid. */ + if (p->pack_fd != -1) return 1; - for (c = p->pack_name, last_c = c; *c;) - if (*c == '/') - last_c = ++c; - else - ++c; - if (!strcmp(last_c, name)) - return 1; + /* If the pack has one window completely covering the + * file size, the pack is known to be valid even if + * the descriptor is not currently open. + */ + if (p->windows) { + struct pack_window *w = p->windows; - return 0; + if (!w->offset && w->len == p->pack_size) + return 1; + } + + /* Force the pack to open to prove its valid. */ + return !open_packed_git(p); } -static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e, const char **ignore_packed) +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; @@ -1894,15 +1993,6 @@ static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e, cons p = (last_found == (void *)1) ? packed_git : last_found; do { - if (ignore_packed) { - const char **ig; - for (ig = ignore_packed; *ig; ig++) - if (matches_pack_name(p, *ig)) - break; - if (*ig) - goto next; - } - if (p->num_bad_objects) { unsigned i; for (i = 0; i < p->num_bad_objects; i++) @@ -1920,7 +2010,7 @@ static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e, cons * it may have been deleted since the index * was loaded! */ - if (p->pack_fd == -1 && open_packed_git(p)) { + if (!is_pack_valid(p)) { error("packfile %s cannot be accessed", p->pack_name); goto next; } @@ -1973,17 +2063,25 @@ static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *size status = error("unable to parse %s header", sha1_to_hex(sha1)); else if (sizep) *sizep = size; - inflateEnd(&stream); + git_inflate_end(&stream); munmap(map, mapsize); return status; } int sha1_object_info(const unsigned char *sha1, unsigned long *sizep) { + struct cached_object *co; struct pack_entry e; int status; - if (!find_pack_entry(sha1, &e, NULL)) { + co = find_cached_object(sha1); + if (co) { + if (sizep) + *sizep = co->size; + return co->type; + } + + if (!find_pack_entry(sha1, &e)) { /* Most likely it's a loose object. */ status = sha1_loose_object_info(sha1, sizep); if (status >= 0) @@ -1991,10 +2089,17 @@ int sha1_object_info(const unsigned char *sha1, unsigned long *sizep) /* Not a loose object; someone else may have just packed it. */ reprepare_packed_git(); - if (!find_pack_entry(sha1, &e, NULL)) + if (!find_pack_entry(sha1, &e)) return status; } - return packed_object_info(e.p, e.offset, sizep); + + status = packed_object_info(e.p, e.offset, sizep); + if (status < 0) { + mark_bad_packed_object(e.p, sha1); + status = sha1_object_info(sha1, sizep); + } + + return status; } static void *read_packed_sha1(const unsigned char *sha1, @@ -2003,7 +2108,7 @@ static void *read_packed_sha1(const unsigned char *sha1, struct pack_entry e; void *data; - if (!find_pack_entry(sha1, &e, NULL)) + if (!find_pack_entry(sha1, &e)) return NULL; data = cache_or_unpack_entry(e.p, e.offset, size, type, 1); if (!data) { @@ -2021,43 +2126,6 @@ static void *read_packed_sha1(const unsigned char *sha1, return data; } -/* - * 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 - * to write them into the object store (e.g. a browse-only - * application). - */ -static struct cached_object { - unsigned char sha1[20]; - enum object_type type; - void *buf; - unsigned long size; -} *cached_objects; -static int cached_object_nr, cached_object_alloc; - -static struct cached_object empty_tree = { - /* empty tree sha1: 4b825dc642cb6eb9a060e54bf8d69288fbee4904 */ - "\x4b\x82\x5d\xc6\x42\xcb\x6e\xb9\xa0\x60" - "\xe5\x4b\xf8\xd6\x92\x88\xfb\xee\x49\x04", - OBJ_TREE, - "", - 0 -}; - -static struct cached_object *find_cached_object(const unsigned char *sha1) -{ - int i; - struct cached_object *co = cached_objects; - - for (i = 0; i < cached_object_nr; i++, co++) { - if (!hashcmp(co->sha1, sha1)) - return co; - } - if (!hashcmp(sha1, empty_tree.sha1)) - return &empty_tree; - return NULL; -} - int pretend_sha1_file(void *buf, unsigned long len, enum object_type type, unsigned char *sha1) { @@ -2081,8 +2149,8 @@ int pretend_sha1_file(void *buf, unsigned long len, enum object_type type, return 0; } -void *read_object(const unsigned char *sha1, enum object_type *type, - unsigned long *size) +static void *read_object(const unsigned char *sha1, enum object_type *type, + unsigned long *size) { unsigned long mapsize; void *map, *buf; @@ -2108,14 +2176,48 @@ void *read_object(const unsigned char *sha1, enum object_type *type, return read_packed_sha1(sha1, type, size); } -void *read_sha1_file(const unsigned char *sha1, enum object_type *type, - unsigned long *size) +/* + * This function dies on corrupt objects; the callers who want to + * deal with them should arrange to call read_object() and give error + * messages themselves. + */ +void *read_sha1_file_repl(const unsigned char *sha1, + enum object_type *type, + unsigned long *size, + const unsigned char **replacement) { - void *data = read_object(sha1, type, size); - /* legacy behavior is to die on corrupted objects */ - if (!data && (has_loose_object(sha1) || has_packed_and_bad(sha1))) - die("object %s is corrupted", sha1_to_hex(sha1)); - return data; + const unsigned char *repl = lookup_replace_object(sha1); + void *data; + char *path; + const struct packed_git *p; + + errno = 0; + data = read_object(repl, type, size); + if (data) { + if (replacement) + *replacement = repl; + return data; + } + + if (errno && errno != ENOENT) + die_errno("failed to read object %s", sha1_to_hex(sha1)); + + /* die if we replaced an object with one that does not exist */ + if (repl != sha1) + die("replacement %s not found for %s", + sha1_to_hex(repl), sha1_to_hex(sha1)); + + if (has_loose_object(repl)) { + path = sha1_file_name(sha1); + die("loose object %s (stored in %s) is corrupt", + sha1_to_hex(repl), path); + } + + if ((p = has_packed_and_bad(repl)) != NULL) + die("packed object %s (stored in %s) is corrupt", + sha1_to_hex(repl), p->pack_name); + + return NULL; } void *read_object_with_reference(const unsigned char *sha1, @@ -2170,25 +2272,31 @@ static void write_sha1_file_prepare(const void *buf, unsigned long len, const char *type, unsigned char *sha1, char *hdr, int *hdrlen) { - SHA_CTX c; + git_SHA_CTX c; /* Generate the header */ *hdrlen = sprintf(hdr, "%s %lu", type, len)+1; /* Sha1.. */ - SHA1_Init(&c); - SHA1_Update(&c, hdr, *hdrlen); - SHA1_Update(&c, buf, len); - SHA1_Final(sha1, &c); + git_SHA1_Init(&c); + git_SHA1_Update(&c, hdr, *hdrlen); + git_SHA1_Update(&c, buf, len); + git_SHA1_Final(sha1, &c); } /* - * Move the just written object into its final resting place + * Move the just written object into its final resting place. + * NEEDSWORK: this should be renamed to finalize_temp_file() as + * "moving" is only a part of what it does, when no patch between + * master to pu changes the call sites of this function. */ int move_temp_to_file(const char *tmpfile, const char *filename) { int ret = 0; - if (link(tmpfile, filename)) + + if (object_creation_mode == OBJECT_CREATION_USES_RENAMES) + goto try_rename; + else if (link(tmpfile, filename)) ret = errno; /* @@ -2199,15 +2307,16 @@ int move_temp_to_file(const char *tmpfile, const char *filename) * * The same holds for FAT formatted media. * - * When this succeeds, we just return 0. We have nothing + * When this succeeds, we just return. We have nothing * left to unlink. */ if (ret && ret != EEXIST) { + try_rename: if (!rename(tmpfile, filename)) - return 0; + goto out; ret = errno; } - unlink(tmpfile); + unlink_or_warn(tmpfile); if (ret) { if (ret != EEXIST) { return error("unable to write sha1 filename %s: %s\n", filename, strerror(ret)); @@ -2215,6 +2324,9 @@ int move_temp_to_file(const char *tmpfile, const char *filename) /* FIXME!!! Collision check here ? */ } +out: + if (adjust_shared_perm(filename)) + return error("unable to set permission to '%s'", filename); return 0; } @@ -2239,9 +2351,8 @@ static void close_sha1_file(int fd) { if (fsync_object_files) fsync_or_die(fd, "sha1 file"); - fchmod(fd, 0444); if (close(fd) != 0) - die("error when closing sha1 file (%s)", strerror(errno)); + die_errno("error when closing sha1 file"); } /* Size of directory component, including the ending '/' */ @@ -2270,7 +2381,7 @@ static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename) } memcpy(buffer, filename, dirlen); strcpy(buffer + dirlen, "tmp_obj_XXXXXX"); - fd = mkstemp(buffer); + fd = git_mkstemp_mode(buffer, 0444); if (fd < 0 && dirlen && errno == ENOENT) { /* Make sure the directory exists */ memcpy(buffer, filename, dirlen); @@ -2280,18 +2391,19 @@ static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename) /* Try again */ strcpy(buffer + dirlen - 1, "/tmp_obj_XXXXXX"); - fd = mkstemp(buffer); + fd = git_mkstemp_mode(buffer, 0444); } return fd; } static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen, - void *buf, unsigned long len, time_t mtime) + const void *buf, unsigned long len, time_t mtime) { int fd, ret; - size_t size; - unsigned char *compressed; + unsigned char compressed[4096]; z_stream stream; + git_SHA_CTX c; + unsigned char parano_sha1[20]; char *filename; static char tmpfile[PATH_MAX]; @@ -2307,36 +2419,40 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen, /* Set it up */ memset(&stream, 0, sizeof(stream)); deflateInit(&stream, zlib_compression_level); - size = 8 + deflateBound(&stream, len+hdrlen); - compressed = xmalloc(size); - - /* Compress it */ stream.next_out = compressed; - stream.avail_out = size; + stream.avail_out = sizeof(compressed); + git_SHA1_Init(&c); /* First header.. */ stream.next_in = (unsigned char *)hdr; stream.avail_in = hdrlen; while (deflate(&stream, 0) == Z_OK) /* nothing */; + git_SHA1_Update(&c, hdr, hdrlen); /* Then the data itself.. */ - stream.next_in = buf; + stream.next_in = (void *)buf; stream.avail_in = len; - ret = deflate(&stream, Z_FINISH); + do { + unsigned char *in0 = stream.next_in; + ret = deflate(&stream, Z_FINISH); + git_SHA1_Update(&c, in0, stream.next_in - in0); + if (write_buffer(fd, compressed, stream.next_out - compressed) < 0) + die("unable to write sha1 file"); + stream.next_out = compressed; + stream.avail_out = sizeof(compressed); + } while (ret == Z_OK); + if (ret != Z_STREAM_END) die("unable to deflate new object %s (%d)", sha1_to_hex(sha1), ret); - ret = deflateEnd(&stream); if (ret != Z_OK) die("deflateEnd on object %s failed (%d)", sha1_to_hex(sha1), ret); + git_SHA1_Final(parano_sha1, &c); + if (hashcmp(sha1, parano_sha1) != 0) + die("confused by unstable object source data for %s", sha1_to_hex(sha1)); - size = stream.total_out; - - if (write_buffer(fd, compressed, size) < 0) - die("unable to write sha1 file"); close_sha1_file(fd); - free(compressed); if (mtime) { struct utimbuf utb; @@ -2350,7 +2466,7 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen, return move_temp_to_file(tmpfile, filename); } -int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *returnsha1) +int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *returnsha1) { unsigned char sha1[20]; char hdr[32]; @@ -2396,74 +2512,36 @@ int has_pack_index(const unsigned char *sha1) return 1; } -int has_pack_file(const unsigned char *sha1) -{ - struct stat st; - if (stat(sha1_pack_name(sha1), &st)) - return 0; - return 1; -} - -int has_sha1_pack(const unsigned char *sha1, const char **ignore_packed) +int has_sha1_pack(const unsigned char *sha1) { struct pack_entry e; - return find_pack_entry(sha1, &e, ignore_packed); + return find_pack_entry(sha1, &e); } int has_sha1_file(const unsigned char *sha1) { struct pack_entry e; - if (find_pack_entry(sha1, &e, NULL)) + if (find_pack_entry(sha1, &e)) return 1; return has_loose_object(sha1); } -int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object) +static int index_mem(unsigned char *sha1, void *buf, size_t size, + int write_object, enum object_type type, const char *path) { - struct strbuf buf; - int ret; - - strbuf_init(&buf, 0); - if (strbuf_read(&buf, fd, 4096) < 0) { - strbuf_release(&buf); - return -1; - } - - if (!type) - type = blob_type; - if (write_object) - ret = write_sha1_file(buf.buf, buf.len, type, sha1); - else - ret = hash_sha1_file(buf.buf, buf.len, type, sha1); - strbuf_release(&buf); - - return ret; -} - -int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, - enum object_type type, const char *path) -{ - size_t size = xsize_t(st->st_size); - void *buf = NULL; int ret, re_allocated = 0; - if (size) - buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); - close(fd); - if (!type) type = OBJ_BLOB; /* * Convert blobs to git internal format */ - if ((type == OBJ_BLOB) && S_ISREG(st->st_mode)) { - struct strbuf nbuf; - strbuf_init(&nbuf, 0); + if ((type == OBJ_BLOB) && path) { + struct strbuf nbuf = STRBUF_INIT; if (convert_to_git(path, buf, size, &nbuf, write_object ? safe_crlf : 0)) { - munmap(buf, size); buf = strbuf_detach(&nbuf, &size); re_allocated = 1; } @@ -2473,20 +2551,50 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, ret = write_sha1_file(buf, size, typename(type), sha1); else ret = hash_sha1_file(buf, size, typename(type), sha1); - if (re_allocated) { + if (re_allocated) free(buf); - return ret; - } - if (size) + return ret; +} + +#define SMALL_FILE_SIZE (32*1024) + +int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, + enum object_type type, const char *path) +{ + int ret; + size_t size = xsize_t(st->st_size); + + if (!S_ISREG(st->st_mode)) { + struct strbuf sbuf = STRBUF_INIT; + if (strbuf_read(&sbuf, fd, 4096) >= 0) + ret = index_mem(sha1, sbuf.buf, sbuf.len, write_object, + type, path); + else + ret = -1; + strbuf_release(&sbuf); + } else if (!size) { + ret = index_mem(sha1, NULL, size, write_object, type, path); + } else if (size <= SMALL_FILE_SIZE) { + char *buf = xmalloc(size); + if (size == read_in_full(fd, buf, size)) + ret = index_mem(sha1, buf, size, write_object, type, + path); + else + ret = error("short read %s", strerror(errno)); + free(buf); + } else { + void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); + ret = index_mem(sha1, buf, size, write_object, type, path); munmap(buf, size); + } + close(fd); return ret; } int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object) { int fd; - char *target; - size_t len; + struct strbuf sb = STRBUF_INIT; switch (st->st_mode & S_IFMT) { case S_IFREG: @@ -2499,20 +2607,17 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, int write path); break; case S_IFLNK: - len = xsize_t(st->st_size); - target = xmalloc(len + 1); - if (readlink(path, target, len + 1) != st->st_size) { + if (strbuf_readlink(&sb, path, st->st_size)) { char *errstr = strerror(errno); - free(target); return error("readlink(\"%s\"): %s", path, errstr); } if (!write_object) - hash_sha1_file(target, len, blob_type, sha1); - else if (write_sha1_file(target, len, blob_type, sha1)) + hash_sha1_file(sb.buf, sb.len, blob_type, sha1); + else if (write_sha1_file(sb.buf, sb.len, blob_type, sha1)) return error("%s: failed to insert into database", path); - free(target); + strbuf_release(&sb); break; case S_IFDIR: return resolve_gitlink_ref(path, "HEAD", sha1); @@ -2536,3 +2641,13 @@ int read_pack_header(int fd, struct pack_header *header) return PH_ERROR_PROTOCOL; return 0; } + +void assert_sha1_type(const unsigned char *sha1, enum object_type expect) +{ + enum object_type type = sha1_object_info(sha1, NULL); + if (type < 0) + die("%s is not a valid object", sha1_to_hex(sha1)); + if (type != expect) + die("%s is not a valid '%s' object", sha1_to_hex(sha1), + typename(expect)); +} |