diff options
Diffstat (limited to 'sha1_file.c')
| -rw-r--r-- | sha1_file.c | 340 |
1 files changed, 194 insertions, 146 deletions
diff --git a/sha1_file.c b/sha1_file.c index bcfcab351d..63981fb3fd 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -99,7 +99,11 @@ 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)) { @@ -250,7 +254,6 @@ 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 +284,7 @@ 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); @@ -394,6 +397,16 @@ 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; @@ -707,6 +720,8 @@ static int open_packed_git_1(struct packed_git *p) return error("packfile %s index unavailable", p->pack_name); p->pack_fd = open(p->pack_name, O_RDONLY); + while (p->pack_fd < 0 && errno == EMFILE && unuse_one_window(p, -1)) + p->pack_fd = open(p->pack_name, O_RDONLY); if (p->pack_fd < 0 || fstat(p->pack_fd, &st)) return -1; @@ -778,7 +793,7 @@ 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) @@ -788,7 +803,7 @@ unsigned char* use_pack(struct packed_git *p, 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. @@ -924,6 +939,8 @@ static void prepare_packed_git_one(char *objdir, int local) sprintf(path, "%s/pack", objdir); len = strlen(path); dir = opendir(path); + while (!dir && errno == EMFILE && unuse_one_window(packed_git, -1)) + dir = opendir(path); if (!dir) { if (errno != ENOENT) error("unable to open object pack directory: %s: %s", @@ -1141,11 +1158,11 @@ 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 +1170,10 @@ 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 +1200,8 @@ 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 +1212,7 @@ 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 +1221,7 @@ 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", @@ -1241,11 +1258,11 @@ 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 +1352,19 @@ 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 +1405,7 @@ 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 +1431,32 @@ 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 +1478,11 @@ 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 +1566,9 @@ 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; @@ -1549,16 +1587,18 @@ static void *unpack_compressed_entry(struct packed_git *p, buffer[size] = 0; 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 +1642,9 @@ 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 +1713,9 @@ 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 +1744,12 @@ 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 +1778,8 @@ 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 +1787,20 @@ 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 +1924,7 @@ off_t find_pack_entry_one(const unsigned char *sha1, return 0; } -int matches_pack_name(struct packed_git *p, const char *name) -{ - const char *last_c, *c; - - if (!strcmp(p->pack_name, name)) - 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; - - return 0; -} - -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 +1936,6 @@ 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++) @@ -1973,7 +2006,7 @@ 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; } @@ -1983,7 +2016,7 @@ int sha1_object_info(const unsigned char *sha1, unsigned long *sizep) struct pack_entry e; int status; - if (!find_pack_entry(sha1, &e, NULL)) { + 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 +2024,17 @@ 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 +2043,7 @@ 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) { @@ -2036,9 +2076,7 @@ static struct cached_object { 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", + EMPTY_TREE_SHA1_BIN, OBJ_TREE, "", 0 @@ -2081,8 +2119,8 @@ 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; @@ -2108,13 +2146,26 @@ 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) +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); + const unsigned char *repl = lookup_replace_object(sha1); + void *data = read_object(repl, type, size); + + /* die if we replaced an object with one that does not exist */ + if (!data && repl != sha1) + die("replacement %s not found for %s", + sha1_to_hex(repl), sha1_to_hex(sha1)); + /* 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)); + if (!data && (has_loose_object(repl) || has_packed_and_bad(repl))) + die("object %s is corrupted", sha1_to_hex(repl)); + + if (replacement) + *replacement = repl; + return data; } @@ -2170,25 +2221,31 @@ 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 +2256,16 @@ 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 +2273,9 @@ int move_temp_to_file(const char *tmpfile, const char *filename) /* FIXME!!! Collision check here ? */ } +out: + if (set_shared_perm(filename, (S_IFREG|0444))) + return error("unable to set permission to '%s'", filename); return 0; } @@ -2239,9 +2300,8 @@ 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 '/' */ @@ -2297,6 +2357,8 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen, filename = sha1_file_name(sha1); fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename); + while (fd < 0 && errno == EMFILE && unuse_one_window(packed_git, -1)) + fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename); if (fd < 0) { if (errno == EACCES) return error("insufficient permission for adding an object to repository database %s\n", get_object_directory()); @@ -2404,66 +2466,36 @@ int has_pack_file(const unsigned char *sha1) 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) -{ - 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) +static int index_mem(unsigned char *sha1, void *buf, size_t size, + 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 +2505,39 @@ 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; +} + +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) { + void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); + ret = index_mem(sha1, buf, size, write_object, type, path); munmap(buf, size); + } else + ret = index_mem(sha1, NULL, size, write_object, type, path); + 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 +2550,17 @@ 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); |