diff options
Diffstat (limited to 'sha1_file.c')
| -rw-r--r-- | sha1_file.c | 926 |
1 files changed, 616 insertions, 310 deletions
diff --git a/sha1_file.c b/sha1_file.c index c23cc5e6e1..4ccaf7ac19 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -11,11 +11,15 @@ #include "pack.h" #include "blob.h" #include "commit.h" +#include "run-command.h" #include "tag.h" #include "tree.h" +#include "tree-walk.h" #include "refs.h" #include "pack-revindex.h" #include "sha1-lookup.h" +#include "bulk-checkin.h" +#include "streaming.h" #ifndef O_NOATIME #if defined(__linux__) && (defined(__i386__) || defined(__PPC__)) @@ -25,21 +29,75 @@ #endif #endif -#ifdef NO_C99_FORMAT -#define SZ_FMT "lu" -static unsigned long sz_fmt(size_t s) { return (unsigned long)s; } -#else -#define SZ_FMT "zu" -static size_t sz_fmt(size_t s) { return s; } -#endif +#define SZ_FMT PRIuMAX +static inline uintmax_t sz_fmt(size_t s) { return s; } const unsigned char null_sha1[20]; -static inline int offset_1st_component(const char *path) +/* + * 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 +}; + +static struct packed_git *last_found_pack; + +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 mkdir_in_gitdir(const char *path) { - if (has_dos_drive_prefix(path)) - return 2 + (path[2] == '/'); - return *path == '/'; + if (mkdir(path, 0777)) { + int saved_errno = errno; + struct stat st; + struct strbuf sb = STRBUF_INIT; + + if (errno != EEXIST) + return -1; + /* + * Are we looking at a path in a symlinked worktree + * whose original repository does not yet have it? + * e.g. .git/rr-cache pointing at its original + * repository in which the user hasn't performed any + * conflict resolution yet? + */ + if (lstat(path, &st) || !S_ISLNK(st.st_mode) || + strbuf_readlink(&sb, path, st.st_size) || + !is_absolute_path(sb.buf) || + mkdir(sb.buf, 0777)) { + strbuf_release(&sb); + errno = saved_errno; + return -1; + } + strbuf_release(&sb); + } + return adjust_shared_perm(path); } int safe_create_leading_directories(char *path) @@ -109,20 +167,22 @@ 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, @@ -169,7 +229,7 @@ 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); /* * Prepare alternate object database registry. @@ -191,27 +251,30 @@ static int link_alt_odb_entry(const char * entry, int len, const char * relative const char *objdir = get_object_directory(); struct alternate_object_database *ent; struct alternate_object_database *alt; - /* 43 = 40-byte + 2 '/' + terminating NUL */ - int pfxlen = len; - int entlen = pfxlen + 43; - int base_len = -1; + int pfxlen, entlen; + struct strbuf pathbuf = STRBUF_INIT; if (!is_absolute_path(entry) && relative_base) { - /* Relative alt-odb */ - if (base_len < 0) - base_len = strlen(relative_base) + 1; - entlen += base_len; - pfxlen += base_len; + strbuf_addstr(&pathbuf, real_path(relative_base)); + strbuf_addch(&pathbuf, '/'); } - ent = xmalloc(sizeof(*ent) + entlen); + strbuf_add(&pathbuf, entry, len); - if (!is_absolute_path(entry) && relative_base) { - memcpy(ent->base, relative_base, base_len - 1); - ent->base[base_len - 1] = '/'; - memcpy(ent->base + base_len, entry, len); - } - else - memcpy(ent->base, entry, pfxlen); + normalize_path_copy(pathbuf.buf, pathbuf.buf); + + pfxlen = strlen(pathbuf.buf); + + /* + * The trailing slash after the directory name is given by + * this function at the end. Remove duplicates. + */ + while (pfxlen && pathbuf.buf[pfxlen-1] == '/') + pfxlen -= 1; + + entlen = pfxlen + 43; /* '/' + 2 hex + '/' + 38 hex + NUL */ + ent = xmalloc(sizeof(*ent) + entlen); + memcpy(ent->base, pathbuf.buf, pfxlen); + strbuf_release(&pathbuf); ent->name = ent->base + pfxlen + 1; ent->base[pfxlen + 3] = '/'; @@ -290,7 +353,7 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep, } } -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; @@ -303,7 +366,7 @@ 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); if (fd < 0) return; if (fstat(fd, &st) || (st.st_size == 0)) { @@ -323,7 +386,7 @@ void add_to_alternates_file(const char *reference) { struct lock_file *lock = xcalloc(1, sizeof(struct lock_file)); int fd = hold_lock_file_for_append(lock, git_path("objects/info/alternates"), LOCK_DIE_ON_ERROR); - char *alt = mkpath("%s/objects\n", reference); + char *alt = mkpath("%s\n", reference); write_or_die(fd, alt, strlen(alt)); if (commit_lock_file(lock)) die("could not close alternates file"); @@ -385,6 +448,8 @@ 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; @@ -416,7 +481,7 @@ 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); struct stat st; if (fd < 0) @@ -562,8 +627,10 @@ 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; } } @@ -581,6 +648,21 @@ 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) { @@ -606,6 +688,14 @@ 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 @@ -625,12 +715,15 @@ 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; + if (last_found_pack == p) + last_found_pack = NULL; free(p); return; } @@ -653,11 +746,29 @@ 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); - while (p->pack_fd < 0 && errno == EMFILE && unuse_one_window(p, -1)) - 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); 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) { @@ -709,6 +820,7 @@ 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; @@ -730,18 +842,17 @@ static int in_window(struct pack_window *win, off_t offset) unsigned char *use_pack(struct packed_git *p, struct pack_window **w_cursor, off_t offset, - unsigned int *left) + unsigned long *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 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?)"); @@ -755,6 +866,10 @@ 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; @@ -772,6 +887,12 @@ 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) @@ -801,11 +922,22 @@ 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. @@ -838,9 +970,8 @@ 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); @@ -856,6 +987,9 @@ 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; } @@ -873,8 +1007,6 @@ 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", @@ -1002,7 +1134,7 @@ 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; @@ -1010,29 +1142,71 @@ 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) +/* + * 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) + break; + git_SHA1_Update(&c, buf, readlen); + } + git_SHA1_Final(real_sha1, &c); + close_istream(st); return hashcmp(sha1, real_sha1) ? -1 : 0; } static int git_open_noatime(const char *name) { 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) @@ -1057,7 +1231,7 @@ static int open_sha1_file(const unsigned char *sha1) return -1; } -static void *map_sha1_file(const unsigned char *sha1, unsigned long *size) +void *map_sha1_file(const unsigned char *sha1, unsigned long *size) { void *map; int fd; @@ -1069,6 +1243,11 @@ static 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); @@ -1076,20 +1255,49 @@ static void *map_sha1_file(const unsigned char *sha1, unsigned long *size) return map; } -static int legacy_loose_object(unsigned char *map) +/* + * There used to be a second loose object header format which + * was meant to mimic the in-pack format, allowing for direct + * copy of the object data. This format turned up not to be + * really worth it and we no longer write loose objects in that + * format. + */ +static int experimental_loose_object(unsigned char *map) { unsigned int word; /* - * Is it a zlib-compressed buffer? If so, the first byte - * must be 0x78 (15-bit window size, deflated), and the - * first 16-bit word is evenly divisible by 31 + * We must determine if the buffer contains the standard + * zlib-deflated stream or the experimental format based + * on the in-pack object format. Compare the header byte + * for each format: + * + * RFC1950 zlib w/ deflate : 0www1000 : 0 <= www <= 7 + * Experimental pack-based : Stttssss : ttt = 1,2,3,4 + * + * If bit 7 is clear and bits 0-3 equal 8, the buffer MUST be + * in standard loose-object format, UNLESS it is a Git-pack + * format object *exactly* 8 bytes in size when inflated. + * + * However, RFC1950 also specifies that the 1st 16-bit word + * must be divisible by 31 - this checksum tells us our buffer + * is in the standard format, giving a false positive only if + * the 1st word of the Git-pack format object happens to be + * divisible by 31, ie: + * ((byte0 * 256) + byte1) % 31 = 0 + * => 0ttt10000www1000 % 31 = 0 + * + * As it happens, this case can only arise for www=3 & ttt=1 + * - ie, a Commit object, which would have to be 8 bytes in + * size. As no Commit can be that small, we find that the + * combination of these two criteria (bitmask & checksum) + * can always correctly determine the buffer format. */ word = (map[0] << 8) + map[1]; - if (map[0] == 0x78 && !(word % 31)) - return 1; - else + if ((map[0] & 0x8F) == 0x08 && !(word % 31)) return 0; + else + return 1; } unsigned long unpack_object_header_buffer(const unsigned char *buf, @@ -1106,7 +1314,8 @@ 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; @@ -1116,7 +1325,7 @@ unsigned long unpack_object_header_buffer(const unsigned char *buf, return used; } -static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz) +int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz) { unsigned long size, used; static const char valid_loose_object_type[8] = { @@ -1133,37 +1342,32 @@ static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned lon stream->next_out = buffer; stream->avail_out = bufsiz; - if (legacy_loose_object(map)) { - git_inflate_init(stream); - return git_inflate(stream, 0); - } - + if (experimental_loose_object(map)) { + /* + * The old experimental format we no longer produce; + * we can still read it. + */ + used = unpack_object_header_buffer(map, mapsize, &type, &size); + if (!used || !valid_loose_object_type[type]) + return -1; + map += used; + mapsize -= used; - /* - * There used to be a second loose object header format which - * was meant to mimic the in-pack format, allowing for direct - * copy of the object data. This format turned up not to be - * really worth it and we don't write it any longer. But we - * can still read it. - */ - used = unpack_object_header_buffer(map, mapsize, &type, &size); - if (!used || !valid_loose_object_type[type]) - return -1; - map += used; - mapsize -= used; + /* Set up the stream for the rest.. */ + stream->next_in = map; + stream->avail_in = mapsize; + git_inflate_init(stream); - /* Set up the stream for the rest.. */ - stream->next_in = map; - stream->avail_in = mapsize; + /* And generate the fake traditional header */ + stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu", + typename(type), size); + return 0; + } git_inflate_init(stream); - - /* And generate the fake traditional header */ - stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu", - typename(type), size); - return 0; + return git_inflate(stream, 0); } -static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size, const unsigned char *sha1) +static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long size, const unsigned char *sha1) { int bytes = strlen(buffer) + 1; unsigned char *buf = xmallocz(size); @@ -1179,7 +1383,7 @@ static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size /* * The above condition must be (bytes <= size), not * (bytes < size). In other words, even though we - * expect no more output and set avail_out to zer0, + * expect no more output and set avail_out to zero, * the input zlib stream may have bytes that express * "this concludes the stream", and we *do* want to * eat that input. @@ -1213,7 +1417,7 @@ static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size * too permissive for what we want to check. So do an anal * object header parse by hand. */ -static int parse_sha1_header(const char *hdr, unsigned long *sizep) +int parse_sha1_header(const char *hdr, unsigned long *sizep) { char type[10]; int i; @@ -1262,7 +1466,7 @@ static int parse_sha1_header(const char *hdr, unsigned long *sizep) static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1) { int ret; - z_stream stream; + git_zstream stream; char hdr[8192]; ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)); @@ -1278,7 +1482,7 @@ unsigned long get_size_from_delta(struct packed_git *p, { const unsigned char *data; unsigned char delta_head[20], *in; - z_stream stream; + git_zstream stream; int st; memset(&stream, 0, sizeof(stream)); @@ -1352,7 +1556,7 @@ static off_t get_delta_base(struct packed_git *p, /* forward declaration for a mutually recursive function */ static int packed_object_info(struct packed_git *p, off_t offset, - unsigned long *sizep); + unsigned long *sizep, int *rtype); static int packed_delta_info(struct packed_git *p, struct pack_window **w_curs, @@ -1366,7 +1570,7 @@ static int packed_delta_info(struct packed_git *p, 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); + type = packed_object_info(p, base_offset, NULL, NULL); if (type <= OBJ_NONE) { struct revindex_entry *revidx; const unsigned char *base_sha1; @@ -1394,18 +1598,18 @@ static int packed_delta_info(struct packed_git *p, return type; } -static int unpack_object_header(struct packed_git *p, - struct pack_window **w_curs, - off_t *curpos, - unsigned long *sizep) +int unpack_object_header(struct packed_git *p, + struct pack_window **w_curs, + off_t *curpos, + unsigned long *sizep) { unsigned char *base; - unsigned int left; + unsigned long left; unsigned long used; enum object_type type; /* use_pack() assures us we have [base, base + 20) available - * as a range that we can look at at. (Its actually the hash + * as a range that we can look at. (Its actually the hash * size that is assured.) With our object header encoding * the maximum deflated object size is 2^137, which is just * insane, so we know won't exceed what we have been given. @@ -1420,63 +1624,8 @@ static int unpack_object_header(struct packed_git *p, return type; } -const char *packed_object_info_detail(struct packed_git *p, - off_t obj_offset, - unsigned long *size, - unsigned long *store_size, - unsigned int *delta_chain_length, - unsigned char *base_sha1) -{ - struct pack_window *w_curs = NULL; - off_t curpos; - unsigned long dummy; - unsigned char *next_sha1; - enum object_type type; - struct revindex_entry *revidx; - - *delta_chain_length = 0; - curpos = obj_offset; - type = unpack_object_header(p, &w_curs, &curpos, size); - - revidx = find_pack_revindex(p, obj_offset); - *store_size = revidx[1].offset - obj_offset; - - for (;;) { - switch (type) { - default: - die("pack %s contains unknown object type %d", - p->pack_name, type); - case OBJ_COMMIT: - case OBJ_TREE: - case OBJ_BLOB: - case OBJ_TAG: - unuse_pack(&w_curs); - return typename(type); - case OBJ_OFS_DELTA: - obj_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset); - if (!obj_offset) - die("pack %s contains bad delta base reference of type %s", - p->pack_name, typename(type)); - if (*delta_chain_length == 0) { - revidx = find_pack_revindex(p, obj_offset); - hashcpy(base_sha1, nth_packed_object_sha1(p, revidx->nr)); - } - break; - case OBJ_REF_DELTA: - next_sha1 = use_pack(p, &w_curs, curpos, NULL); - if (*delta_chain_length == 0) - hashcpy(base_sha1, next_sha1); - obj_offset = find_pack_entry_one(next_sha1, p); - break; - } - (*delta_chain_length)++; - curpos = obj_offset; - type = unpack_object_header(p, &w_curs, &curpos, &dummy); - } -} - static int packed_object_info(struct packed_git *p, off_t obj_offset, - unsigned long *sizep) + unsigned long *sizep, int *rtype) { struct pack_window *w_curs = NULL; unsigned long size; @@ -1484,6 +1633,8 @@ static int packed_object_info(struct packed_git *p, off_t obj_offset, enum object_type type; type = unpack_object_header(p, &w_curs, &curpos, &size); + if (rtype) + *rtype = type; /* representation type */ switch (type) { case OBJ_OFS_DELTA: @@ -1513,7 +1664,7 @@ static void *unpack_compressed_entry(struct packed_git *p, unsigned long size) { int st; - z_stream stream; + git_zstream stream; unsigned char *buffer, *in; buffer = xmallocz(size); @@ -1566,6 +1717,13 @@ 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) +{ + unsigned long hash = pack_entry_hash(p, base_offset); + struct delta_base_cache_entry *ent = delta_base_cache + hash; + return (ent->data && ent->p == p && ent->base_offset == base_offset); +} + 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) { @@ -1710,6 +1868,24 @@ static void *unpack_delta_entry(struct packed_git *p, return result; } +static void write_pack_access_log(struct packed_git *p, off_t obj_offset) +{ + static FILE *log_file; + + 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; + return; + } + } + fprintf(log_file, "%s %"PRIuMAX"\n", + p->pack_name, (uintmax_t)obj_offset); + fflush(log_file); +} + int do_check_packed_object_crc; void *unpack_entry(struct packed_git *p, off_t obj_offset, @@ -1719,6 +1895,9 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset, off_t curpos = obj_offset; void *data; + if (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; @@ -1856,54 +2035,79 @@ off_t find_pack_entry_one(const unsigned char *sha1, return 0; } +int is_pack_valid(struct packed_git *p) +{ + /* An already open pack is known to be valid. */ + if (p->pack_fd != -1) + 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; + + 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 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 (p->pack_fd == -1 && open_packed_git(p)) { - error("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; } @@ -1925,7 +2129,7 @@ static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *size int status; unsigned long mapsize, size; void *map; - z_stream stream; + git_zstream stream; char hdr[32]; map = map_sha1_file(sha1, &mapsize); @@ -1943,16 +2147,28 @@ static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *size return status; } -int sha1_object_info(const unsigned char *sha1, unsigned long *sizep) +/* returns enum object_type or negative */ +int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi) { + struct cached_object *co; struct pack_entry e; - int status; + int status, rtype; + + co = find_cached_object(sha1); + if (co) { + if (oi->sizep) + *(oi->sizep) = co->size; + oi->whence = OI_CACHED; + 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) + status = sha1_loose_object_info(sha1, oi->sizep); + if (status >= 0) { + oi->whence = OI_LOOSE; return status; + } /* Not a loose object; someone else may have just packed it. */ reprepare_packed_git(); @@ -1960,15 +2176,31 @@ int sha1_object_info(const unsigned char *sha1, unsigned long *sizep) return status; } - status = packed_object_info(e.p, e.offset, sizep); + status = packed_object_info(e.p, e.offset, oi->sizep, &rtype); if (status < 0) { mark_bad_packed_object(e.p, sha1); - status = sha1_object_info(sha1, sizep); + status = sha1_object_info_extended(sha1, oi); + } else if (in_delta_base_cache(e.p, e.offset)) { + oi->whence = OI_DBCACHED; + } else { + oi->whence = OI_PACKED; + oi->u.packed.offset = e.offset; + oi->u.packed.pack = e.p; + oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA || + rtype == OBJ_OFS_DELTA); } return status; } +int sha1_object_info(const unsigned char *sha1, unsigned long *sizep) +{ + struct object_info oi; + + oi.sizep = sizep; + return sha1_object_info_extended(sha1, &oi); +} + static void *read_packed_sha1(const unsigned char *sha1, enum object_type *type, unsigned long *size) { @@ -1993,41 +2225,6 @@ 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_BIN, - 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) { @@ -2078,27 +2275,46 @@ static void *read_object(const unsigned char *sha1, enum object_type *type, return read_packed_sha1(sha1, type, size); } -void *read_sha1_file_repl(const unsigned char *sha1, - enum object_type *type, - unsigned long *size, - const unsigned char **replacement) +/* + * 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_extended(const unsigned char *sha1, + enum object_type *type, + unsigned long *size, + unsigned flag) { - const unsigned char *repl = lookup_replace_object(sha1); - void *data = read_object(repl, type, size); + void *data; + char *path; + const struct packed_git *p; + const unsigned char *repl = (flag & READ_SHA1_FILE_REPLACE) + ? lookup_replace_object(sha1) : sha1; + + errno = 0; + data = read_object(repl, type, size); + if (data) + 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 (!data && repl != sha1) + if (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(repl) || has_packed_and_bad(repl))) - die("object %s is corrupted", sha1_to_hex(repl)); + 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 (replacement) - *replacement = repl; + 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 data; + return NULL; } void *read_object_with_reference(const unsigned char *sha1, @@ -2200,7 +2416,7 @@ 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 ? */ } @@ -2278,30 +2494,28 @@ static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename) } 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; unsigned char compressed[4096]; - z_stream stream; + git_zstream stream; 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); - while (fd < 0 && errno == EMFILE && unuse_one_window(packed_git, -1)) - 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 */ memset(&stream, 0, sizeof(stream)); - deflateInit(&stream, zlib_compression_level); + git_deflate_init(&stream, zlib_compression_level); stream.next_out = compressed; stream.avail_out = sizeof(compressed); git_SHA1_Init(&c); @@ -2309,16 +2523,16 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen, /* First header.. */ stream.next_in = (unsigned char *)hdr; stream.avail_in = hdrlen; - while (deflate(&stream, 0) == Z_OK) - /* nothing */; + while (git_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; do { unsigned char *in0 = stream.next_in; - ret = deflate(&stream, Z_FINISH); + ret = git_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"); @@ -2328,7 +2542,7 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen, if (ret != Z_STREAM_END) die("unable to deflate new object %s (%d)", sha1_to_hex(sha1), ret); - ret = deflateEnd(&stream); + ret = git_deflate_end_gently(&stream); if (ret != Z_OK) die("deflateEnd on object %s failed (%d)", sha1_to_hex(sha1), ret); git_SHA1_Final(parano_sha1, &c); @@ -2341,15 +2555,15 @@ 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(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]; @@ -2410,10 +2624,40 @@ int has_sha1_file(const unsigned char *sha1) return has_loose_object(sha1); } +static void check_tree(const void *buf, size_t size) +{ + struct tree_desc desc; + struct name_entry entry; + + init_tree_desc(&desc, buf, size); + while (tree_entry(&desc, &entry)) + /* do nothing + * tree_entry() will die() on malformed entries */ + ; +} + +static void check_commit(const void *buf, size_t size) +{ + struct commit c; + memset(&c, 0, sizeof(c)); + if (parse_commit_buffer(&c, buf, size)) + die("corrupt commit"); +} + +static void check_tag(const void *buf, size_t size) +{ + struct tag t; + memset(&t, 0, sizeof(t)); + if (parse_tag_buffer(&t, buf, size)) + die("corrupt tag"); +} + static int index_mem(unsigned char *sha1, void *buf, size_t size, - int write_object, enum object_type type, const char *path) + enum object_type type, + const char *path, unsigned flags) { int ret, re_allocated = 0; + int write_object = flags & HASH_WRITE_OBJECT; if (!type) type = OBJ_BLOB; @@ -2424,11 +2668,19 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size, if ((type == OBJ_BLOB) && path) { struct strbuf nbuf = STRBUF_INIT; if (convert_to_git(path, buf, size, &nbuf, - write_object ? safe_crlf : 0)) { + write_object ? safe_crlf : SAFE_CRLF_FALSE)) { buf = strbuf_detach(&nbuf, &size); re_allocated = 1; } } + if (flags & HASH_FORMAT_CHECK) { + if (type == OBJ_TREE) + check_tree(buf, size); + if (type == OBJ_COMMIT) + check_commit(buf, size); + if (type == OBJ_TAG) + check_tag(buf, size); + } if (write_object) ret = write_sha1_file(buf, size, typename(type), sha1); @@ -2439,41 +2691,85 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size, return ret; } +static int index_pipe(unsigned char *sha1, int fd, enum object_type type, + const char *path, unsigned flags) +{ + struct strbuf sbuf = STRBUF_INIT; + int ret; + + if (strbuf_read(&sbuf, fd, 4096) >= 0) + ret = index_mem(sha1, sbuf.buf, sbuf.len, type, path, flags); + else + ret = -1; + strbuf_release(&sbuf); + 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) +static int index_core(unsigned char *sha1, int fd, size_t size, + enum object_type type, const char *path, + unsigned flags) { 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); + if (!size) { + ret = index_mem(sha1, NULL, size, type, path, flags); } 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); + ret = index_mem(sha1, buf, size, type, path, flags); else ret = error("short read %s", strerror(errno)); free(buf); - } else if (size) { + } else { void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); - ret = index_mem(sha1, buf, size, write_object, type, path); + ret = index_mem(sha1, buf, size, type, path, flags); munmap(buf, size); - } else - ret = index_mem(sha1, NULL, size, write_object, type, path); + } + return ret; +} + +/* + * 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). 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) +{ + return index_bulk_checkin(sha1, fd, size, type, path, flags); +} + +int index_fd(unsigned char *sha1, int fd, struct stat *st, + enum object_type type, const char *path, unsigned flags) +{ + int ret; + size_t size = xsize_t(st->st_size); + + if (!S_ISREG(st->st_mode)) + ret = index_pipe(sha1, fd, type, path, flags); + 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); close(fd); return ret; } -int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object) +int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned flags) { int fd; struct strbuf sb = STRBUF_INIT; @@ -2484,7 +2780,7 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, int write if (fd < 0) return error("open(\"%s\"): %s", path, strerror(errno)); - if (index_fd(sha1, fd, st, write_object, OBJ_BLOB, path) < 0) + if (index_fd(sha1, fd, st, OBJ_BLOB, path, flags) < 0) return error("%s: failed to insert into database", path); break; @@ -2494,7 +2790,7 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, int write return error("readlink(\"%s\"): %s", path, errstr); } - if (!write_object) + if (!(flags & HASH_WRITE_OBJECT)) 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", @@ -2523,3 +2819,13 @@ 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)); +} |