X-Git-Url: https://git.verplant.org/?a=blobdiff_plain;f=sha1_file.c;h=e27affb2885717974b5612d4a41a91ed390d7ff7;hb=a69d09436687746a898f86f32c180083f323b616;hp=430f5fdfbf0a0f4a226dfcc9af199bb1242a0ad0;hpb=d19938ab6053e3dad75a68a60ef8cad1f378b0e5;p=git.git diff --git a/sha1_file.c b/sha1_file.c index 430f5fdf..e27affb2 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -6,9 +6,10 @@ * This handles basic git sha1 object files - packing, unpacking, * creation etc. */ -#include -#include +#include +#include #include "cache.h" +#include "delta.h" #ifndef O_NOATIME #if defined(__linux__) && (defined(__i386__) || defined(__PPC__)) @@ -44,7 +45,7 @@ int get_sha1_hex(const char *hex, unsigned char *sha1) return 0; } -int get_sha1_file(const char *path, unsigned char *result) +static int get_sha1_file(const char *path, unsigned char *result) { char buffer[60]; int fd = open(path, O_RDONLY); @@ -59,6 +60,47 @@ int get_sha1_file(const char *path, unsigned char *result) return get_sha1_hex(buffer, result); } +static char *git_dir, *git_object_dir, *git_index_file, *git_refs_dir; +static void setup_git_env(void) +{ + git_dir = gitenv(GIT_DIR_ENVIRONMENT); + if (!git_dir) + git_dir = DEFAULT_GIT_DIR_ENVIRONMENT; + git_object_dir = gitenv(DB_ENVIRONMENT); + if (!git_object_dir) { + git_object_dir = xmalloc(strlen(git_dir) + 9); + sprintf(git_object_dir, "%s/objects", git_dir); + } + git_refs_dir = xmalloc(strlen(git_dir) + 6); + sprintf(git_refs_dir, "%s/refs", git_dir); + git_index_file = gitenv(INDEX_ENVIRONMENT); + if (!git_index_file) { + git_index_file = xmalloc(strlen(git_dir) + 7); + sprintf(git_index_file, "%s/index", git_dir); + } +} + +char *get_object_directory(void) +{ + if (!git_object_dir) + setup_git_env(); + return git_object_dir; +} + +char *get_refs_directory(void) +{ + if (!git_refs_dir) + setup_git_env(); + return git_refs_dir; +} + +char *get_index_file(void) +{ + if (!git_index_file) + setup_git_env(); + return git_index_file; +} + int get_sha1(const char *str, unsigned char *sha1) { static char pathname[PATH_MAX]; @@ -70,15 +112,16 @@ int get_sha1(const char *str, unsigned char *sha1) "refs/snap", NULL }; - const char *gitdir; const char **p; if (!get_sha1_hex(str, sha1)) return 0; - gitdir = ".git"; + if (!git_dir) + setup_git_env(); for (p = prefix; *p; p++) { - snprintf(pathname, sizeof(pathname), "%s/%s/%s", gitdir, *p, str); + snprintf(pathname, sizeof(pathname), "%s/%s/%s", + git_dir, *p, str); if (!get_sha1_file(pathname, sha1)) return 0; } @@ -166,7 +209,7 @@ static void prepare_alt_odb(void) { int pass, totlen, i; const char *cp, *last; - char *op = 0; + char *op = NULL; const char *alt = gitenv(ALTERNATE_DB_ENVIRONMENT) ? : ""; /* The first pass counts how large an area to allocate to @@ -203,7 +246,7 @@ static void prepare_alt_odb(void) if (pass) break; alt_odb = xmalloc(sizeof(*alt_odb) * (i + 1) + totlen); - alt_odb[i].base = alt_odb[i].name = 0; + alt_odb[i].base = alt_odb[i].name = NULL; op = (char*)(&alt_odb[i+1]); } } @@ -225,7 +268,185 @@ static char *find_sha1_file(const unsigned char *sha1, struct stat *st) return NULL; } -int check_sha1_signature(unsigned char *sha1, void *map, unsigned long size, const char *type) +#define PACK_MAX_SZ (1<<26) +static int pack_used_ctr; +static unsigned long pack_mapped; +static struct packed_git { + struct packed_git *next; + unsigned long index_size; + unsigned long pack_size; + unsigned int *index_base; + void *pack_base; + unsigned int pack_last_used; + char pack_name[0]; /* something like ".git/objects/pack/xxxxx.pack" */ +} *packed_git; + +struct pack_entry { + unsigned int offset; + unsigned char sha1[20]; + struct packed_git *p; +}; + +static int check_packed_git_idx(const char *path, unsigned long *idx_size_, + void **idx_map_) +{ + void *idx_map; + unsigned int *index; + unsigned long idx_size; + int nr, i; + int fd = open(path, O_RDONLY); + struct stat st; + if (fd < 0) + return -1; + if (fstat(fd, &st)) { + close(fd); + return -1; + } + idx_size = st.st_size; + idx_map = mmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0); + close(fd); + if (idx_map == MAP_FAILED) + return -1; + + index = idx_map; + + /* check index map */ + if (idx_size < 4*256 + 20) + return error("index file too small"); + nr = 0; + for (i = 0; i < 256; i++) { + unsigned int n = ntohl(index[i]); + if (n < nr) + return error("non-monotonic index"); + nr = n; + } + + /* + * Total size: + * - 256 index entries 4 bytes each + * - 24-byte entries * nr (20-byte sha1 + 4-byte offset) + * - 20-byte SHA1 of the packfile + * - 20-byte SHA1 file checksum + */ + if (idx_size != 4*256 + nr * 24 + 20 + 20) + return error("wrong index file size"); + + *idx_map_ = idx_map; + *idx_size_ = idx_size; + return 0; +} + +static void unuse_one_packed_git(void) +{ + /* NOTYET */ +} + +static int use_packed_git(struct packed_git *p) +{ + if (!p->pack_base) { + int fd; + struct stat st; + void *map; + + pack_mapped += p->pack_size; + while (PACK_MAX_SZ < pack_mapped) + unuse_one_packed_git(); + fd = open(p->pack_name, O_RDONLY); + if (fd < 0) + return -1; + if (fstat(fd, &st)) { + close(fd); + return -1; + } + if (st.st_size != p->pack_size) + return -1; + map = mmap(NULL, p->pack_size, PROT_READ, MAP_PRIVATE, fd, 0); + close(fd); + if (map == MAP_FAILED) + return -1; + p->pack_base = map; + } + p->pack_last_used = pack_used_ctr++; + return 0; +} + +static struct packed_git *add_packed_git(char *path, int path_len) +{ + struct stat st; + struct packed_git *p; + unsigned long idx_size; + void *idx_map; + + if (check_packed_git_idx(path, &idx_size, &idx_map)) + return NULL; + + /* do we have a corresponding .pack file? */ + strcpy(path + path_len - 4, ".pack"); + if (stat(path, &st) || !S_ISREG(st.st_mode)) { + munmap(idx_map, idx_size); + return NULL; + } + /* ok, it looks sane as far as we can check without + * actually mapping the pack file. + */ + p = xmalloc(sizeof(*p) + path_len + 2); + strcpy(p->pack_name, path); + p->index_size = idx_size; + p->pack_size = st.st_size; + p->index_base = idx_map; + p->next = NULL; + p->pack_last_used = 0; + return p; +} + +static void prepare_packed_git_one(char *objdir) +{ + char path[PATH_MAX]; + int len; + DIR *dir; + struct dirent *de; + + sprintf(path, "%s/pack", objdir); + len = strlen(path); + dir = opendir(path); + if (!dir) + return; + path[len++] = '/'; + while ((de = readdir(dir)) != NULL) { + int namelen = strlen(de->d_name); + struct packed_git *p; + + if (strcmp(de->d_name + namelen - 4, ".idx")) + continue; + + /* we have .idx. Is it a file we can map? */ + strcpy(path + len, de->d_name); + p = add_packed_git(path, len + namelen); + if (!p) + continue; + p->next = packed_git; + packed_git = p; + } +} + +static void prepare_packed_git(void) +{ + int i; + static int run_once = 0; + + if (run_once++) + return; + + prepare_packed_git_one(get_object_directory()); + if (!alt_odb) + prepare_alt_odb(); + for (i = 0; alt_odb[i].base != NULL; i++) { + alt_odb[i].name[0] = 0; + prepare_packed_git_one(alt_odb[i].base); + } +} + +int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type) { char header[100]; unsigned char real_sha1[20]; @@ -238,7 +459,9 @@ int check_sha1_signature(unsigned char *sha1, void *map, unsigned long size, con return memcmp(sha1, real_sha1, 20) ? -1 : 0; } -void *map_sha1_file(const unsigned char *sha1, unsigned long *size) +static void *map_sha1_file_internal(const unsigned char *sha1, + unsigned long *size, + int say_error) { struct stat st; void *map; @@ -246,7 +469,8 @@ void *map_sha1_file(const unsigned char *sha1, unsigned long *size) char *filename = find_sha1_file(sha1, &st); if (!filename) { - error("cannot map sha1 file %s", sha1_to_hex(sha1)); + if (say_error) + error("cannot map sha1 file %s", sha1_to_hex(sha1)); return NULL; } @@ -260,11 +484,14 @@ void *map_sha1_file(const unsigned char *sha1, unsigned long *size) break; /* Fallthrough */ case 0: - perror(filename); + if (say_error) + perror(filename); return NULL; } - /* If it failed once, it will probably fail again. Stop using O_NOATIME */ + /* If it failed once, it will probably fail again. + * Stop using O_NOATIME + */ sha1_file_open_flag = 0; } map = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0); @@ -275,40 +502,405 @@ void *map_sha1_file(const unsigned char *sha1, unsigned long *size) return map; } +void *map_sha1_file(const unsigned char *sha1, unsigned long *size) +{ + return map_sha1_file_internal(sha1, size, 1); +} + +int unpack_sha1_header(z_stream *stream, void *map, unsigned long mapsize, void *buffer, unsigned long size) +{ + /* Get the data stream */ + memset(stream, 0, sizeof(*stream)); + stream->next_in = map; + stream->avail_in = mapsize; + stream->next_out = buffer; + stream->avail_out = size; + + inflateInit(stream); + return inflate(stream, 0); +} + +void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size) +{ + int bytes = strlen(buffer) + 1; + unsigned char *buf = xmalloc(1+size); + + memcpy(buf, buffer + bytes, stream->total_out - bytes); + bytes = stream->total_out - bytes; + if (bytes < size) { + stream->next_out = buf + bytes; + stream->avail_out = size - bytes; + while (inflate(stream, Z_FINISH) == Z_OK) + /* nothing */; + } + buf[size] = 0; + inflateEnd(stream); + return buf; +} + +/* + * We used to just use "sscanf()", but that's actually way + * too permissive for what we want to check. So do an anal + * object header parse by hand. + */ +int parse_sha1_header(char *hdr, char *type, unsigned long *sizep) +{ + int i; + unsigned long size; + + /* + * The type can be at most ten bytes (including the + * terminating '\0' that we add), and is followed by + * a space. + */ + i = 10; + for (;;) { + char c = *hdr++; + if (c == ' ') + break; + if (!--i) + return -1; + *type++ = c; + } + *type = 0; + + /* + * The length must follow immediately, and be in canonical + * decimal format (ie "010" is not valid). + */ + size = *hdr++ - '0'; + if (size > 9) + return -1; + if (size) { + for (;;) { + unsigned long c = *hdr - '0'; + if (c > 9) + break; + hdr++; + size = size * 10 + c; + } + } + *sizep = size; + + /* + * The length must be followed by a zero byte + */ + return *hdr ? -1 : 0; +} + void * unpack_sha1_file(void *map, unsigned long mapsize, char *type, unsigned long *size) { - int ret, bytes; + int ret; z_stream stream; - char buffer[8192]; - char *buf; + char hdr[8192]; + + ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)); + if (ret < Z_OK || parse_sha1_header(hdr, type, size) < 0) + return NULL; + + return unpack_sha1_rest(&stream, hdr, *size); +} + +static int packed_delta_info(unsigned char *base_sha1, + unsigned long delta_size, + unsigned long left, + char *type, + unsigned long *sizep) +{ + unsigned char *data; + unsigned char delta_head[64]; + int i; + unsigned char cmd; + unsigned long data_size, result_size, base_size, verify_base_size; + z_stream stream; + int st; + + if (left < 20) + die("truncated pack file"); + if (sha1_object_info(base_sha1, type, &base_size)) + die("cannot get info for delta-pack base"); + + data = base_sha1 + 20; + data_size = left - 20; - /* Get the data stream */ memset(&stream, 0, sizeof(stream)); - stream.next_in = map; - stream.avail_in = mapsize; + + stream.next_in = data; + stream.avail_in = data_size; + stream.next_out = delta_head; + stream.avail_out = sizeof(delta_head); + + inflateInit(&stream); + st = inflate(&stream, Z_FINISH); + inflateEnd(&stream); + if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) + die("delta data unpack-initial failed"); + + /* Examine the initial part of the delta to figure out + * the result size. Verify the base size while we are at it. + */ + data = delta_head; + verify_base_size = i = 0; + cmd = *data++; + while (cmd) { + if (cmd & 1) + verify_base_size |= *data++ << i; + i += 8; + cmd >>= 1; + } + + /* Read the result size */ + result_size = i = 0; + cmd = *data++; + while (cmd) { + if (cmd & 1) + result_size |= *data++ << i; + i += 8; + cmd >>= 1; + } + if (verify_base_size != base_size) + die("delta base size mismatch"); + + *sizep = result_size; + return 0; +} + +static int packed_object_info(struct pack_entry *entry, + char *type, unsigned long *sizep) +{ + struct packed_git *p = entry->p; + unsigned long offset, size, left; + unsigned char *pack; + + offset = entry->offset; + if (p->pack_size - 5 < offset) + die("object offset outside of pack file"); + + if (use_packed_git(p)) + die("cannot map packed file"); + + pack = p->pack_base + offset; + size = (pack[1] << 24) + (pack[2] << 16) + (pack[3] << 8) + pack[4]; + left = p->pack_size - offset - 5; + switch (*pack) { + case 'D': + return packed_delta_info(pack+5, size, left, type, sizep); + break; + case 'C': + strcpy(type, "commit"); + break; + case 'T': + strcpy(type, "tree"); + break; + case 'B': + strcpy(type, "blob"); + break; + case 'G': + strcpy(type, "tag"); + break; + default: + die("corrupted pack file"); + } + *sizep = size; + return 0; +} + +/* forward declaration for a mutually recursive function */ +static void *unpack_entry(struct pack_entry *, char *, unsigned long *); + +static void *unpack_delta_entry(unsigned char *base_sha1, + unsigned long delta_size, + unsigned long left, + char *type, + unsigned long *sizep) +{ + void *data, *delta_data, *result, *base; + unsigned long data_size, result_size, base_size; + z_stream stream; + int st; + + if (left < 20) + die("truncated pack file"); + data = base_sha1 + 20; + data_size = left - 20; + delta_data = xmalloc(delta_size); + + memset(&stream, 0, sizeof(stream)); + + stream.next_in = data; + stream.avail_in = data_size; + stream.next_out = delta_data; + stream.avail_out = delta_size; + + inflateInit(&stream); + st = inflate(&stream, Z_FINISH); + inflateEnd(&stream); + if ((st != Z_STREAM_END) || stream.total_out != delta_size) + die("delta data unpack failed"); + + /* This may recursively unpack the base, which is what we want */ + base = read_sha1_file(base_sha1, type, &base_size); + if (!base) + die("failed to read delta-pack base object %s", + sha1_to_hex(base_sha1)); + result = patch_delta(base, base_size, + delta_data, delta_size, + &result_size); + if (!result) + die("failed to apply delta"); + free(delta_data); + free(base); + *sizep = result_size; + return result; +} + +static void *unpack_non_delta_entry(unsigned char *data, + unsigned long size, + unsigned long left) +{ + int st; + z_stream stream; + char *buffer; + + buffer = xmalloc(size + 1); + buffer[size] = 0; + memset(&stream, 0, sizeof(stream)); + stream.next_in = data; + stream.avail_in = left; stream.next_out = buffer; - stream.avail_out = sizeof(buffer); + stream.avail_out = size; inflateInit(&stream); - ret = inflate(&stream, 0); - if (ret < Z_OK) - return NULL; - if (sscanf(buffer, "%10s %lu", type, size) != 2) + st = inflate(&stream, Z_FINISH); + inflateEnd(&stream); + if ((st != Z_STREAM_END) || stream.total_out != size) { + free(buffer); return NULL; + } - bytes = strlen(buffer) + 1; - buf = xmalloc(*size); + return buffer; +} - memcpy(buf, buffer + bytes, stream.total_out - bytes); - bytes = stream.total_out - bytes; - if (bytes < *size && ret == Z_OK) { - stream.next_out = buf + bytes; - stream.avail_out = *size - bytes; - while (inflate(&stream, Z_FINISH) == Z_OK) - /* nothing */; +static void *unpack_entry(struct pack_entry *entry, + char *type, unsigned long *sizep) +{ + struct packed_git *p = entry->p; + unsigned long offset, size, left; + unsigned char *pack; + + offset = entry->offset; + if (p->pack_size - 5 < offset) + die("object offset outside of pack file"); + + if (use_packed_git(p)) + die("cannot map packed file"); + + pack = p->pack_base + offset; + size = (pack[1] << 24) + (pack[2] << 16) + (pack[3] << 8) + pack[4]; + left = p->pack_size - offset - 5; + switch (*pack) { + case 'D': + return unpack_delta_entry(pack+5, size, left, type, sizep); + case 'C': + strcpy(type, "commit"); + break; + case 'T': + strcpy(type, "tree"); + break; + case 'B': + strcpy(type, "blob"); + break; + case 'G': + strcpy(type, "tag"); + break; + default: + die("corrupted pack file"); + } + *sizep = size; + return unpack_non_delta_entry(pack+5, size, left); +} + +static int find_pack_entry_1(const unsigned char *sha1, + struct pack_entry *e, struct packed_git *p) +{ + int *level1_ofs = p->index_base; + int hi = ntohl(level1_ofs[*sha1]); + int lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1])); + void *index = p->index_base + 256; + + do { + int mi = (lo + hi) / 2; + int cmp = memcmp(index + 24 * mi + 4, sha1, 20); + if (!cmp) { + e->offset = ntohl(*((int*)(index + 24 * mi))); + memcpy(e->sha1, sha1, 20); + e->p = p; + return 1; + } + if (cmp > 0) + hi = mi; + else + lo = mi+1; + } while (lo < hi); + return 0; +} + +static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e) +{ + struct packed_git *p; + prepare_packed_git(); + + for (p = packed_git; p; p = p->next) { + if (find_pack_entry_1(sha1, e, p)) + return 1; + } + return 0; +} + +int sha1_object_info(const unsigned char *sha1, char *type, unsigned long *sizep) +{ + int status; + unsigned long mapsize, size; + void *map; + z_stream stream; + char hdr[128]; + + map = map_sha1_file_internal(sha1, &mapsize, 0); + if (!map) { + struct pack_entry e; + + if (!find_pack_entry(sha1, &e)) + return error("unable to find %s", sha1_to_hex(sha1)); + if (!packed_object_info(&e, type, sizep)) + return 0; + /* sheesh */ + map = unpack_entry(&e, type, sizep); + free(map); + return (map == NULL) ? 0 : -1; + } + if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0) + status = error("unable to unpack %s header", + sha1_to_hex(sha1)); + if (parse_sha1_header(hdr, type, &size) < 0) + status = error("unable to parse %s header", sha1_to_hex(sha1)); + else { + status = 0; + *sizep = size; } inflateEnd(&stream); - return buf; + munmap(map, mapsize); + return status; +} + +static void *read_packed_sha1(const unsigned char *sha1, char *type, unsigned long *size) +{ + struct pack_entry e; + + if (!find_pack_entry(sha1, &e)) { + error("cannot read sha1_file for %s", sha1_to_hex(sha1)); + return NULL; + } + return unpack_entry(&e, type, size); } void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size) @@ -316,17 +908,17 @@ void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size unsigned long mapsize; void *map, *buf; - map = map_sha1_file(sha1, &mapsize); + map = map_sha1_file_internal(sha1, &mapsize, 0); if (map) { buf = unpack_sha1_file(map, mapsize, type, size); munmap(map, mapsize); return buf; } - return NULL; + return read_packed_sha1(sha1, type, size); } void *read_object_with_reference(const unsigned char *sha1, - const unsigned char *required_type, + const char *required_type, unsigned long *size, unsigned char *actual_sha1_return) { @@ -370,31 +962,46 @@ void *read_object_with_reference(const unsigned char *sha1, } } -int write_sha1_file(char *buf, unsigned long len, const char *type, unsigned char *returnsha1) +static char *write_sha1_file_prepare(void *buf, + unsigned long len, + const char *type, + unsigned char *sha1, + unsigned char *hdr, + int *hdrlen) { - int size; - char *compressed; - z_stream stream; - unsigned char sha1[20]; SHA_CTX c; - char *filename; - static char tmpfile[PATH_MAX]; - char hdr[50]; - int fd, hdrlen, ret; /* Generate the header */ - hdrlen = sprintf(hdr, "%s %lu", type, len)+1; + *hdrlen = sprintf((char *)hdr, "%s %lu", type, len)+1; /* Sha1.. */ SHA1_Init(&c); - SHA1_Update(&c, hdr, hdrlen); + SHA1_Update(&c, hdr, *hdrlen); SHA1_Update(&c, buf, len); SHA1_Final(sha1, &c); + return sha1_file_name(sha1); +} + +int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *returnsha1) +{ + int size; + unsigned char *compressed; + z_stream stream; + unsigned char sha1[20]; + char *filename; + static char tmpfile[PATH_MAX]; + unsigned char hdr[50]; + int fd, hdrlen, ret; + + /* Normally if we have it in the pack then we do not bother writing + * it out into .git/objects/??/?{38} file. + */ + filename = write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen); if (returnsha1) memcpy(returnsha1, sha1, 20); - - filename = sha1_file_name(sha1); + if (has_sha1_file(sha1)) + return 0; fd = open(filename, O_RDONLY); if (fd >= 0) { /* @@ -432,7 +1039,7 @@ int write_sha1_file(char *buf, unsigned long len, const char *type, unsigned cha stream.next_in = hdr; stream.avail_in = hdrlen; while (deflate(&stream, 0) == Z_OK) - /* nothing */ + /* nothing */; /* Then the data itself.. */ stream.next_in = buf; @@ -483,8 +1090,8 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd) int local; z_stream stream; unsigned char real_sha1[20]; - char buf[4096]; - char discard[4096]; + unsigned char buf[4096]; + unsigned char discard[4096]; int ret; SHA_CTX c; @@ -541,7 +1148,11 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd) int has_sha1_file(const unsigned char *sha1) { struct stat st; - return !!find_sha1_file(sha1, &st); + struct pack_entry e; + + if (find_sha1_file(sha1, &st)) + return 1; + return find_pack_entry(sha1, &e); } int index_fd(unsigned char *sha1, int fd, struct stat *st)