#endif
#endif
+#ifdef NO_C99_FORMAT
+#define SZ_FMT "lu"
+#else
+#define SZ_FMT "zu"
+#endif
+
const unsigned char null_sha1[20];
static unsigned int sha1_file_open_flag = O_NOATIME;
static void read_info_alternates(const char * relative_base, int depth)
{
char *map;
+ size_t mapsz;
struct stat st;
char path[PATH_MAX];
int fd;
close(fd);
return;
}
- map = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+ mapsz = xsize_t(st.st_size);
+ map = xmmap(NULL, mapsz, PROT_READ, MAP_PRIVATE, fd, 0);
close(fd);
- if (map == MAP_FAILED)
- return;
- link_alt_odb_entries(map, map + st.st_size, '\n', relative_base, depth);
+ link_alt_odb_entries(map, map + mapsz, '\n', relative_base, depth);
- munmap(map, st.st_size);
+ munmap(map, mapsz);
}
void prepare_alt_odb(void)
return NULL;
}
-#define PACK_MAX_SZ (1<<26)
-static int pack_used_ctr;
-static unsigned long pack_mapped;
+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 size_t peak_pack_mapped;
+static size_t pack_mapped;
struct packed_git *packed_git;
-static int check_packed_git_idx(const char *path, unsigned long *idx_size_,
- void **idx_map_)
+void pack_report()
+{
+ fprintf(stderr,
+ "pack_report: getpagesize() = %10" SZ_FMT "\n"
+ "pack_report: core.packedGitWindowSize = %10" SZ_FMT "\n"
+ "pack_report: core.packedGitLimit = %10" SZ_FMT "\n",
+ (size_t) getpagesize(),
+ packed_git_window_size,
+ packed_git_limit);
+ fprintf(stderr,
+ "pack_report: pack_used_ctr = %10u\n"
+ "pack_report: pack_mmap_calls = %10u\n"
+ "pack_report: pack_open_windows = %10u / %10u\n"
+ "pack_report: pack_mapped = "
+ "%10" SZ_FMT " / %10" SZ_FMT "\n",
+ pack_used_ctr,
+ pack_mmap_calls,
+ pack_open_windows, peak_pack_open_windows,
+ pack_mapped, peak_pack_mapped);
+}
+
+static int check_packed_git_idx(const char *path, struct packed_git *p)
{
void *idx_map;
- unsigned int *index;
- unsigned long idx_size;
- int nr, i;
+ struct pack_idx_header *hdr;
+ size_t idx_size;
+ uint32_t nr, i, *index;
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);
+ idx_size = xsize_t(st.st_size);
+ if (idx_size < 4 * 256 + 20 + 20) {
+ close(fd);
+ return error("index file %s is too small", path);
+ }
+ idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0);
close(fd);
- if (idx_map == MAP_FAILED)
- return -1;
- index = idx_map;
- *idx_map_ = idx_map;
- *idx_size_ = idx_size;
+ /* a future index format would start with this, as older git
+ * binaries would fail the non-monotonic index check below.
+ * give a nicer warning to the user if we can.
+ */
+ hdr = idx_map;
+ if (hdr->idx_signature == htonl(PACK_IDX_SIGNATURE)) {
+ munmap(idx_map, idx_size);
+ return error("index file %s is a newer version"
+ " and is not supported by this binary"
+ " (try upgrading GIT to a newer version)",
+ path);
+ }
- /* check index map */
- if (idx_size < 4*256 + 20 + 20)
- return error("index file too small");
nr = 0;
+ index = idx_map;
for (i = 0; i < 256; i++) {
- unsigned int n = ntohl(index[i]);
- if (n < nr)
- return error("non-monotonic index");
+ uint32_t n = ntohl(index[i]);
+ if (n < nr) {
+ munmap(idx_map, idx_size);
+ return error("non-monotonic index %s", path);
+ }
nr = n;
}
* - 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");
+ if (idx_size != 4*256 + nr * 24 + 20 + 20) {
+ munmap(idx_map, idx_size);
+ return error("wrong index file size in %s", path);
+ }
+ p->index_version = 1;
+ p->index_data = idx_map;
+ p->index_size = idx_size;
return 0;
}
-static int unuse_one_packed_git(void)
+static void scan_windows(struct packed_git *p,
+ struct packed_git **lru_p,
+ struct pack_window **lru_w,
+ struct pack_window **lru_l)
{
- struct packed_git *p, *lru = NULL;
+ struct pack_window *w, *w_l;
- for (p = packed_git; p; p = p->next) {
- if (p->pack_use_cnt || !p->pack_base)
- continue;
- if (!lru || p->pack_last_used < lru->pack_last_used)
- lru = p;
+ for (w_l = NULL, w = p->windows; w; w = w->next) {
+ if (!w->inuse_cnt) {
+ if (!*lru_w || w->last_used < (*lru_w)->last_used) {
+ *lru_p = p;
+ *lru_w = w;
+ *lru_l = w_l;
+ }
+ }
+ w_l = w;
}
- if (!lru)
- return 0;
- munmap(lru->pack_base, lru->pack_size);
- lru->pack_base = NULL;
- return 1;
}
-void unuse_packed_git(struct packed_git *p)
+static int unuse_one_window(struct packed_git *current)
+{
+ struct packed_git *p, *lru_p = NULL;
+ struct pack_window *lru_w = NULL, *lru_l = NULL;
+
+ if (current)
+ scan_windows(current, &lru_p, &lru_w, &lru_l);
+ for (p = packed_git; p; p = p->next)
+ scan_windows(p, &lru_p, &lru_w, &lru_l);
+ if (lru_p) {
+ munmap(lru_w->base, lru_w->len);
+ pack_mapped -= lru_w->len;
+ if (lru_l)
+ lru_l->next = lru_w->next;
+ else {
+ lru_p->windows = lru_w->next;
+ if (!lru_p->windows && lru_p != current) {
+ close(lru_p->pack_fd);
+ lru_p->pack_fd = -1;
+ }
+ }
+ free(lru_w);
+ pack_open_windows--;
+ return 1;
+ }
+ return 0;
+}
+
+void release_pack_memory(size_t need)
+{
+ size_t cur = pack_mapped;
+ while (need >= (cur - pack_mapped) && unuse_one_window(NULL))
+ ; /* nothing */
+}
+
+void unuse_pack(struct pack_window **w_cursor)
{
- p->pack_use_cnt--;
+ struct pack_window *w = *w_cursor;
+ if (w) {
+ w->inuse_cnt--;
+ *w_cursor = NULL;
+ }
}
-int use_packed_git(struct packed_git *p)
+/*
+ * Do not call this directly as this leaks p->pack_fd on error return;
+ * call open_packed_git() instead.
+ */
+static int open_packed_git_1(struct packed_git *p)
{
+ struct stat st;
+ struct pack_header hdr;
+ unsigned char sha1[20];
+ unsigned char *idx_sha1;
+ long fd_flag;
+
+ p->pack_fd = open(p->pack_name, O_RDONLY);
+ if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
+ return -1;
+
+ /* If we created the struct before we had the pack we lack size. */
if (!p->pack_size) {
- struct stat st;
- /* We created the struct before we had the pack */
- stat(p->pack_name, &st);
if (!S_ISREG(st.st_mode))
- die("packfile %s not a regular file", p->pack_name);
+ return error("packfile %s not a regular file", p->pack_name);
p->pack_size = st.st_size;
+ } else if (p->pack_size != st.st_size)
+ return error("packfile %s size changed", p->pack_name);
+
+ /* We leave these file descriptors open with sliding mmap;
+ * there is no point keeping them open across exec(), though.
+ */
+ fd_flag = fcntl(p->pack_fd, F_GETFD, 0);
+ if (fd_flag < 0)
+ return error("cannot determine file descriptor flags");
+ fd_flag |= FD_CLOEXEC;
+ if (fcntl(p->pack_fd, F_SETFD, fd_flag) == -1)
+ return error("cannot set FD_CLOEXEC");
+
+ /* Verify we recognize this pack file format. */
+ if (read_in_full(p->pack_fd, &hdr, sizeof(hdr)) != sizeof(hdr))
+ return error("file %s is far too short to be a packfile", p->pack_name);
+ if (hdr.hdr_signature != htonl(PACK_SIGNATURE))
+ return error("file %s is not a GIT packfile", p->pack_name);
+ if (!pack_version_ok(hdr.hdr_version))
+ return error("packfile %s is version %u and not supported"
+ " (try upgrading GIT to a newer version)",
+ p->pack_name, ntohl(hdr.hdr_version));
+
+ /* Verify the pack matches its index. */
+ if (num_packed_objects(p) != ntohl(hdr.hdr_entries))
+ return error("packfile %s claims to have %u objects"
+ " while index size indicates %u objects",
+ p->pack_name, ntohl(hdr.hdr_entries),
+ num_packed_objects(p));
+ if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1)
+ return error("end of packfile %s is unavailable", p->pack_name);
+ if (read_in_full(p->pack_fd, sha1, sizeof(sha1)) != sizeof(sha1))
+ return error("packfile %s signature is unavailable", p->pack_name);
+ idx_sha1 = ((unsigned char *)p->index_data) + p->index_size - 40;
+ if (hashcmp(sha1, idx_sha1))
+ return error("packfile %s does not match index", p->pack_name);
+ return 0;
+}
+
+static int open_packed_git(struct packed_git *p)
+{
+ if (!open_packed_git_1(p))
+ return 0;
+ if (p->pack_fd != -1) {
+ close(p->pack_fd);
+ p->pack_fd = -1;
}
- if (!p->pack_base) {
- int fd;
- struct stat st;
- void *map;
- struct pack_header *hdr;
+ return -1;
+}
- pack_mapped += p->pack_size;
- while (PACK_MAX_SZ < pack_mapped && unuse_one_packed_git())
- ; /* nothing */
- fd = open(p->pack_name, O_RDONLY);
- if (fd < 0)
- die("packfile %s cannot be opened", p->pack_name);
- if (fstat(fd, &st)) {
- close(fd);
- die("packfile %s cannot be opened", p->pack_name);
- }
- if (st.st_size != p->pack_size)
- die("packfile %s size mismatch.", p->pack_name);
- map = mmap(NULL, p->pack_size, PROT_READ, MAP_PRIVATE, fd, 0);
- close(fd);
- if (map == MAP_FAILED)
- die("packfile %s cannot be mapped.", p->pack_name);
- p->pack_base = map;
+static int in_window(struct pack_window *win, off_t offset)
+{
+ /* We must promise at least 20 bytes (one hash) after the
+ * offset is available from this window, otherwise the offset
+ * is not actually in this window and a different window (which
+ * has that one hash excess) must be used. This is to support
+ * the object header and delta base parsing routines below.
+ */
+ off_t win_off = win->offset;
+ return win_off <= offset
+ && (offset + 20) <= (win_off + win->len);
+}
- /* Check if we understand this pack file. If we don't we're
- * likely too old to handle it.
- */
- hdr = map;
- if (hdr->hdr_signature != htonl(PACK_SIGNATURE))
- die("packfile %s isn't actually a pack.", p->pack_name);
- if (!pack_version_ok(hdr->hdr_version))
- die("packfile %s is version %i and not supported"
- " (try upgrading GIT to a newer version)",
- p->pack_name, ntohl(hdr->hdr_version));
-
- /* Check if the pack file matches with the index file.
- * this is cheap.
- */
- if (hashcmp((unsigned char *)(p->index_base) +
- p->index_size - 40,
- (unsigned char *)p->pack_base +
- p->pack_size - 20)) {
- die("packfile %s does not match index.", p->pack_name);
+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
+ * 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 (offset > (p->pack_size - 20))
+ die("offset beyond end of packfile (truncated pack?)");
+
+ if (!win || !in_window(win, offset)) {
+ if (win)
+ win->inuse_cnt--;
+ for (win = p->windows; win; win = win->next) {
+ if (in_window(win, offset))
+ break;
+ }
+ if (!win) {
+ size_t window_align = packed_git_window_size / 2;
+ off_t len;
+ win = xcalloc(1, sizeof(*win));
+ win->offset = (offset / window_align) * window_align;
+ len = p->pack_size - win->offset;
+ if (len > packed_git_window_size)
+ len = packed_git_window_size;
+ win->len = (size_t)len;
+ pack_mapped += win->len;
+ while (packed_git_limit < pack_mapped
+ && unuse_one_window(p))
+ ; /* nothing */
+ win->base = xmmap(NULL, win->len,
+ PROT_READ, MAP_PRIVATE,
+ p->pack_fd, win->offset);
+ if (win->base == MAP_FAILED)
+ die("packfile %s cannot be mapped: %s",
+ p->pack_name,
+ strerror(errno));
+ pack_mmap_calls++;
+ pack_open_windows++;
+ if (pack_mapped > peak_pack_mapped)
+ peak_pack_mapped = pack_mapped;
+ if (pack_open_windows > peak_pack_open_windows)
+ peak_pack_open_windows = pack_open_windows;
+ win->next = p->windows;
+ p->windows = win;
}
}
- p->pack_last_used = pack_used_ctr++;
- p->pack_use_cnt++;
- return 0;
+ if (win != *w_cursor) {
+ win->last_used = pack_used_ctr++;
+ win->inuse_cnt++;
+ *w_cursor = win;
+ }
+ offset -= win->offset;
+ if (left)
+ *left = win->len - xsize_t(offset);
+ return win->base + offset;
}
-struct packed_git *add_packed_git(char *path, int path_len, int local)
+struct packed_git *add_packed_git(const char *path, int path_len, int local)
{
struct stat st;
- struct packed_git *p;
- unsigned long idx_size;
- void *idx_map;
- unsigned char sha1[20];
+ struct packed_git *p = xmalloc(sizeof(*p) + path_len + 2);
- if (check_packed_git_idx(path, &idx_size, &idx_map))
+ /*
+ * Make sure a corresponding .pack file exists and that
+ * the index looks sane.
+ */
+ path_len -= strlen(".idx");
+ if (path_len < 1)
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);
+ memcpy(p->pack_name, path, path_len);
+ strcpy(p->pack_name + path_len, ".pack");
+ if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode) ||
+ check_packed_git_idx(path, p)) {
+ free(p);
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_base = NULL;
- p->pack_last_used = 0;
- p->pack_use_cnt = 0;
+ p->windows = NULL;
+ p->pack_fd = -1;
p->pack_local = local;
- if ((path_len > 44) && !get_sha1_hex(path + path_len - 44, sha1))
- hashcpy(p->sha1, sha1);
+ p->mtime = st.st_mtime;
+ if (path_len < 40 || get_sha1_hex(path + path_len - 40, p->sha1))
+ hashclr(p->sha1);
return p;
}
return parse_pack_index_file(sha1, path);
}
-struct packed_git *parse_pack_index_file(const unsigned char *sha1, char *idx_path)
+struct packed_git *parse_pack_index_file(const unsigned char *sha1,
+ const char *idx_path)
{
- struct packed_git *p;
- unsigned long idx_size;
- void *idx_map;
- char *path;
+ const char *path = sha1_pack_name(sha1);
+ struct packed_git *p = xmalloc(sizeof(*p) + strlen(path) + 2);
- if (check_packed_git_idx(idx_path, &idx_size, &idx_map))
+ if (check_packed_git_idx(idx_path, p)) {
+ free(p);
return NULL;
+ }
- path = sha1_pack_name(sha1);
-
- p = xmalloc(sizeof(*p) + strlen(path) + 2);
strcpy(p->pack_name, path);
- p->index_size = idx_size;
p->pack_size = 0;
- p->index_base = idx_map;
p->next = NULL;
- p->pack_base = NULL;
- p->pack_last_used = 0;
- p->pack_use_cnt = 0;
+ p->windows = NULL;
+ p->pack_fd = -1;
hashcpy(p->sha1, sha1);
return p;
}
if (!has_extension(de->d_name, ".idx"))
continue;
- /* we have .idx. Is it a file we can map? */
+ /* Don't reopen a pack we already have. */
strcpy(path + len, de->d_name);
for (p = packed_git; p; p = p->next) {
if (!memcmp(path, p->pack_name, len + namelen - 4))
}
if (p)
continue;
+ /* See if it really is a valid .idx file with corresponding
+ * .pack file that we can map.
+ */
p = add_packed_git(path, len + namelen, local);
if (!p)
continue;
- p->next = packed_git;
- packed_git = p;
+ install_packed_git(p);
}
closedir(dir);
}
+static int sort_pack(const void *a_, const void *b_)
+{
+ struct packed_git *a = *((struct packed_git **)a_);
+ struct packed_git *b = *((struct packed_git **)b_);
+ int st;
+
+ /*
+ * Local packs tend to contain objects specific to our
+ * variant of the project than remote ones. In addition,
+ * remote ones could be on a network mounted filesystem.
+ * Favor local ones for these reasons.
+ */
+ st = a->pack_local - b->pack_local;
+ if (st)
+ return -st;
+
+ /*
+ * Younger packs tend to contain more recent objects,
+ * and more recent objects tend to get accessed more
+ * often.
+ */
+ if (a->mtime < b->mtime)
+ return 1;
+ else if (a->mtime == b->mtime)
+ return 0;
+ return -1;
+}
+
+static void rearrange_packed_git(void)
+{
+ struct packed_git **ary, *p;
+ int i, n;
+
+ for (n = 0, p = packed_git; p; p = p->next)
+ n++;
+ if (n < 2)
+ return;
+
+ /* prepare an array of packed_git for easier sorting */
+ ary = xcalloc(n, sizeof(struct packed_git *));
+ for (n = 0, p = packed_git; p; p = p->next)
+ ary[n++] = p;
+
+ qsort(ary, n, sizeof(struct packed_git *), sort_pack);
+
+ /* link them back again */
+ for (i = 0; i < n - 1; i++)
+ ary[i]->next = ary[i + 1];
+ ary[n - 1]->next = NULL;
+ packed_git = ary[0];
+
+ free(ary);
+}
+
static int prepare_packed_git_run_once = 0;
void prepare_packed_git(void)
{
prepare_packed_git_one(alt->base, 0);
alt->name[-1] = '/';
}
+ rearrange_packed_git();
prepare_packed_git_run_once = 1;
}
*/
sha1_file_open_flag = 0;
}
- map = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+ *size = xsize_t(st.st_size);
+ map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0);
close(fd);
- if (map == MAP_FAILED)
- return NULL;
- *size = st.st_size;
return map;
}
/* And generate the fake traditional header */
stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
- type_names[type], size);
+ typename(type), size);
return 0;
}
-static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size)
+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 long n;
+ int status = Z_OK;
n = stream->total_out - bytes;
if (n > size)
n = size;
memcpy(buf, (char *) buffer + bytes, n);
bytes = n;
- if (bytes < size) {
+ if (bytes <= 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,
+ * the input zlib stream may have bytes that express
+ * "this concludes the stream", and we *do* want to
+ * eat that input.
+ *
+ * Otherwise we would not be able to test that we
+ * consumed all the input to reach the expected size;
+ * we also want to check that zlib tells us that all
+ * went well with status == Z_STREAM_END at the end.
+ */
stream->next_out = buf + bytes;
stream->avail_out = size - bytes;
- while (inflate(stream, Z_FINISH) == Z_OK)
- /* nothing */;
+ while (status == Z_OK)
+ status = inflate(stream, Z_FINISH);
}
buf[size] = 0;
- inflateEnd(stream);
- return buf;
+ if (status == Z_STREAM_END && !stream->avail_in) {
+ inflateEnd(stream);
+ return buf;
+ }
+
+ if (status < 0)
+ error("corrupt loose object '%s'", sha1_to_hex(sha1));
+ else if (stream->avail_in)
+ error("garbage at end of loose object '%s'",
+ sha1_to_hex(sha1));
+ free(buf);
+ return NULL;
}
/*
* too permissive for what we want to check. So do an anal
* object header parse by hand.
*/
-static int parse_sha1_header(char *hdr, char *type, unsigned long *sizep)
+static int parse_sha1_header(const char *hdr, unsigned long *sizep)
{
+ char type[10];
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.
+ * a space.
*/
- i = 10;
+ i = 0;
for (;;) {
char c = *hdr++;
if (c == ' ')
break;
- if (!--i)
+ type[i++] = c;
+ if (i >= sizeof(type))
return -1;
- *type++ = c;
}
- *type = 0;
+ type[i] = 0;
/*
* The length must follow immediately, and be in canonical
/*
* The length must be followed by a zero byte
*/
- return *hdr ? -1 : 0;
+ return *hdr ? -1 : type_from_string(type);
}
-void * unpack_sha1_file(void *map, unsigned long mapsize, char *type, unsigned long *size)
+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;
char hdr[8192];
ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr));
- if (ret < Z_OK || parse_sha1_header(hdr, type, size) < 0)
+ if (ret < Z_OK || (*type = parse_sha1_header(hdr, size)) < 0)
return NULL;
- return unpack_sha1_rest(&stream, hdr, *size);
+ return unpack_sha1_rest(&stream, hdr, *size, sha1);
}
-static unsigned long get_delta_base(struct packed_git *p,
- unsigned long offset,
- enum object_type kind,
- unsigned long delta_obj_offset,
- unsigned long *base_obj_offset)
+static off_t get_delta_base(struct packed_git *p,
+ struct pack_window **w_curs,
+ off_t *curpos,
+ enum object_type type,
+ off_t delta_obj_offset)
{
- unsigned char *base_info = (unsigned char *) p->pack_base + offset;
- unsigned long base_offset;
-
- /* there must be at least 20 bytes left regardless of delta type */
- if (p->pack_size <= offset + 20)
- die("truncated pack file");
+ unsigned char *base_info = use_pack(p, w_curs, *curpos, NULL);
+ off_t base_offset;
- if (kind == OBJ_OFS_DELTA) {
+ /* use_pack() assured us we have [base_info, base_info + 20)
+ * as a range that we can look at without walking off the
+ * end of the mapped window. Its actually the hash size
+ * that is assured. An OFS_DELTA longer than the hash size
+ * is stupid, as then a REF_DELTA would be smaller to store.
+ */
+ if (type == OBJ_OFS_DELTA) {
unsigned used = 0;
unsigned char c = base_info[used++];
base_offset = c & 127;
base_offset = delta_obj_offset - base_offset;
if (base_offset >= delta_obj_offset)
die("delta base offset out of bound");
- offset += used;
- } else if (kind == OBJ_REF_DELTA) {
+ *curpos += used;
+ } else if (type == OBJ_REF_DELTA) {
/* The base entry _must_ be in the same pack */
base_offset = find_pack_entry_one(base_info, p);
if (!base_offset)
die("failed to find delta-pack base object %s",
sha1_to_hex(base_info));
- offset += 20;
+ *curpos += 20;
} else
die("I am totally screwed");
- *base_obj_offset = base_offset;
- return offset;
+ return base_offset;
}
/* forward declaration for a mutually recursive function */
-static int packed_object_info(struct packed_git *p, unsigned long offset,
- char *type, unsigned long *sizep);
+static int packed_object_info(struct packed_git *p, off_t offset,
+ unsigned long *sizep);
static int packed_delta_info(struct packed_git *p,
- unsigned long offset,
- enum object_type kind,
- unsigned long obj_offset,
- char *type,
+ struct pack_window **w_curs,
+ off_t curpos,
+ enum object_type type,
+ off_t obj_offset,
unsigned long *sizep)
{
- unsigned long base_offset;
+ off_t base_offset;
- offset = get_delta_base(p, offset, kind, obj_offset, &base_offset);
+ base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset);
+ type = packed_object_info(p, base_offset, NULL);
/* 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 (packed_object_info(p, base_offset, type, NULL))
- die("cannot get info for delta-pack base");
-
if (sizep) {
const unsigned char *data;
- unsigned char delta_head[20];
- unsigned long result_size;
+ unsigned char delta_head[20], *in;
z_stream stream;
int st;
memset(&stream, 0, sizeof(stream));
-
- stream.next_in = (unsigned char *) p->pack_base + offset;
- stream.avail_in = p->pack_size - offset;
stream.next_out = delta_head;
stream.avail_out = sizeof(delta_head);
inflateInit(&stream);
- st = inflate(&stream, Z_FINISH);
+ do {
+ in = use_pack(p, w_curs, curpos, &stream.avail_in);
+ stream.next_in = in;
+ st = 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))
get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
/* Read the result size */
- result_size = get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
- *sizep = result_size;
+ *sizep = get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
}
- return 0;
+
+ return type;
}
-static unsigned long unpack_object_header(struct packed_git *p, unsigned long offset,
- enum object_type *type, unsigned long *sizep)
+static 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 used;
+ enum object_type type;
- if (p->pack_size <= offset)
- die("object offset outside of pack file");
-
- used = unpack_object_header_gently((unsigned char *)p->pack_base +
- offset,
- p->pack_size - offset, type, sizep);
+ /* use_pack() assures us we have [base, base + 20) available
+ * as a range that we can look at 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.
+ */
+ 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;
- return offset + used;
+ return type;
}
-void packed_object_info_detail(struct packed_git *p,
- unsigned long offset,
- char *type,
- unsigned long *size,
- unsigned long *store_size,
- unsigned int *delta_chain_length,
- unsigned char *base_sha1)
+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)
{
- unsigned long obj_offset, val;
+ struct pack_window *w_curs = NULL;
+ off_t curpos;
+ unsigned long dummy;
unsigned char *next_sha1;
- enum object_type kind;
+ enum object_type type;
*delta_chain_length = 0;
- obj_offset = offset;
- offset = unpack_object_header(p, offset, &kind, size);
+ curpos = obj_offset;
+ type = unpack_object_header(p, &w_curs, &curpos, size);
for (;;) {
- switch (kind) {
+ switch (type) {
default:
- die("corrupted pack file %s containing object of kind %d",
- p->pack_name, kind);
+ die("pack %s contains unknown object type %d",
+ p->pack_name, type);
case OBJ_COMMIT:
case OBJ_TREE:
case OBJ_BLOB:
case OBJ_TAG:
- strcpy(type, type_names[kind]);
*store_size = 0; /* notyet */
- return;
+ unuse_pack(&w_curs);
+ return typename(type);
case OBJ_OFS_DELTA:
- get_delta_base(p, offset, kind, obj_offset, &offset);
+ obj_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset);
if (*delta_chain_length == 0) {
- /* TODO: find base_sha1 as pointed by offset */
+ /* TODO: find base_sha1 as pointed by curpos */
+ hashclr(base_sha1);
}
break;
case OBJ_REF_DELTA:
- if (p->pack_size <= offset + 20)
- die("pack file %s records an incomplete delta base",
- p->pack_name);
- next_sha1 = (unsigned char *) p->pack_base + offset;
+ next_sha1 = use_pack(p, &w_curs, curpos, NULL);
if (*delta_chain_length == 0)
hashcpy(base_sha1, next_sha1);
- offset = find_pack_entry_one(next_sha1, p);
+ obj_offset = find_pack_entry_one(next_sha1, p);
break;
}
- obj_offset = offset;
- offset = unpack_object_header(p, offset, &kind, &val);
(*delta_chain_length)++;
+ curpos = obj_offset;
+ type = unpack_object_header(p, &w_curs, &curpos, &dummy);
}
}
-static int packed_object_info(struct packed_git *p, unsigned long offset,
- char *type, unsigned long *sizep)
+static int packed_object_info(struct packed_git *p, off_t obj_offset,
+ unsigned long *sizep)
{
- unsigned long size, obj_offset = offset;
- enum object_type kind;
+ struct pack_window *w_curs = NULL;
+ unsigned long size;
+ off_t curpos = obj_offset;
+ enum object_type type;
- offset = unpack_object_header(p, offset, &kind, &size);
+ type = unpack_object_header(p, &w_curs, &curpos, &size);
- switch (kind) {
+ switch (type) {
case OBJ_OFS_DELTA:
case OBJ_REF_DELTA:
- return packed_delta_info(p, offset, kind, obj_offset, type, sizep);
+ type = packed_delta_info(p, &w_curs, curpos,
+ type, obj_offset, sizep);
+ break;
case OBJ_COMMIT:
case OBJ_TREE:
case OBJ_BLOB:
case OBJ_TAG:
- strcpy(type, type_names[kind]);
+ if (sizep)
+ *sizep = size;
break;
default:
- die("corrupted pack file %s containing object of kind %d",
- p->pack_name, kind);
+ die("pack %s contains unknown object type %d",
+ p->pack_name, type);
}
- if (sizep)
- *sizep = size;
- return 0;
+ unuse_pack(&w_curs);
+ return type;
}
static void *unpack_compressed_entry(struct packed_git *p,
- unsigned long offset,
+ struct pack_window **w_curs,
+ off_t curpos,
unsigned long size)
{
int st;
z_stream stream;
- unsigned char *buffer;
+ unsigned char *buffer, *in;
buffer = xmalloc(size + 1);
buffer[size] = 0;
memset(&stream, 0, sizeof(stream));
- stream.next_in = (unsigned char*)p->pack_base + offset;
- stream.avail_in = p->pack_size - offset;
stream.next_out = buffer;
stream.avail_out = size;
inflateInit(&stream);
- st = inflate(&stream, Z_FINISH);
+ do {
+ in = use_pack(p, w_curs, curpos, &stream.avail_in);
+ stream.next_in = in;
+ st = inflate(&stream, Z_FINISH);
+ curpos += stream.next_in - in;
+ } while (st == Z_OK || st == Z_BUF_ERROR);
inflateEnd(&stream);
if ((st != Z_STREAM_END) || stream.total_out != size) {
free(buffer);
return buffer;
}
+#define MAX_DELTA_CACHE (256)
+
+static size_t delta_base_cached;
+
+static struct delta_base_cache_lru_list {
+ struct delta_base_cache_lru_list *prev;
+ struct delta_base_cache_lru_list *next;
+} delta_base_cache_lru = { &delta_base_cache_lru, &delta_base_cache_lru };
+
+static struct delta_base_cache_entry {
+ struct delta_base_cache_lru_list lru;
+ void *data;
+ struct packed_git *p;
+ off_t base_offset;
+ unsigned long size;
+ enum object_type type;
+} delta_base_cache[MAX_DELTA_CACHE];
+
+static unsigned long pack_entry_hash(struct packed_git *p, off_t base_offset)
+{
+ unsigned long hash;
+
+ hash = (unsigned long)p + (unsigned long)base_offset;
+ hash += (hash >> 8) + (hash >> 16);
+ return hash % MAX_DELTA_CACHE;
+}
+
+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)
+{
+ void *ret;
+ unsigned long hash = pack_entry_hash(p, base_offset);
+ struct delta_base_cache_entry *ent = delta_base_cache + hash;
+
+ ret = ent->data;
+ if (ret && ent->p == p && ent->base_offset == base_offset)
+ goto found_cache_entry;
+ 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;
+ ent->lru.prev->next = ent->lru.next;
+ delta_base_cached -= ent->size;
+ }
+ else {
+ ret = xmalloc(ent->size + 1);
+ memcpy(ret, ent->data, ent->size);
+ ((char *)ret)[ent->size] = 0;
+ }
+ *type = ent->type;
+ *base_size = ent->size;
+ return ret;
+}
+
+static inline void release_delta_base_cache(struct delta_base_cache_entry *ent)
+{
+ if (ent->data) {
+ free(ent->data);
+ ent->data = NULL;
+ ent->lru.next->prev = ent->lru.prev;
+ ent->lru.prev->next = ent->lru.next;
+ delta_base_cached -= ent->size;
+ }
+}
+
+static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
+ void *base, unsigned long base_size, enum object_type type)
+{
+ unsigned long hash = pack_entry_hash(p, base_offset);
+ struct delta_base_cache_entry *ent = delta_base_cache + hash;
+ struct delta_base_cache_lru_list *lru;
+
+ release_delta_base_cache(ent);
+ delta_base_cached += base_size;
+
+ for (lru = delta_base_cache_lru.next;
+ delta_base_cached > delta_base_cache_limit
+ && lru != &delta_base_cache_lru;
+ lru = lru->next) {
+ struct delta_base_cache_entry *f = (void *)lru;
+ if (f->type == OBJ_BLOB)
+ release_delta_base_cache(f);
+ }
+ for (lru = delta_base_cache_lru.next;
+ delta_base_cached > delta_base_cache_limit
+ && lru != &delta_base_cache_lru;
+ lru = lru->next) {
+ struct delta_base_cache_entry *f = (void *)lru;
+ release_delta_base_cache(f);
+ }
+
+ ent->p = p;
+ ent->base_offset = base_offset;
+ ent->type = type;
+ ent->data = base;
+ ent->size = base_size;
+ ent->lru.next = &delta_base_cache_lru;
+ ent->lru.prev = delta_base_cache_lru.prev;
+ delta_base_cache_lru.prev->next = &ent->lru;
+ delta_base_cache_lru.prev = &ent->lru;
+}
+
static void *unpack_delta_entry(struct packed_git *p,
- unsigned long offset,
+ struct pack_window **w_curs,
+ off_t curpos,
unsigned long delta_size,
- enum object_type kind,
- unsigned long obj_offset,
- char *type,
+ off_t obj_offset,
+ enum object_type *type,
unsigned long *sizep)
{
void *delta_data, *result, *base;
- unsigned long result_size, base_size, base_offset;
+ unsigned long base_size;
+ off_t base_offset;
- offset = get_delta_base(p, offset, kind, obj_offset, &base_offset);
- base = unpack_entry_gently(p, base_offset, type, &base_size);
+ base_offset = get_delta_base(p, w_curs, &curpos, *type, obj_offset);
+ base = cache_or_unpack_entry(p, base_offset, &base_size, type, 0);
if (!base)
- die("failed to read delta base object at %lu from %s",
- base_offset, p->pack_name);
+ die("failed to read delta base object"
+ " at %"PRIuMAX" from %s",
+ (uintmax_t)base_offset, p->pack_name);
- delta_data = unpack_compressed_entry(p, offset, delta_size);
+ delta_data = unpack_compressed_entry(p, w_curs, curpos, delta_size);
result = patch_delta(base, base_size,
delta_data, delta_size,
- &result_size);
+ sizep);
if (!result)
die("failed to apply delta");
free(delta_data);
- free(base);
- *sizep = result_size;
+ add_delta_base_cache(p, base_offset, base, base_size, *type);
return result;
}
-static void *unpack_entry(struct pack_entry *entry,
- char *type, unsigned long *sizep)
-{
- struct packed_git *p = entry->p;
- void *retval;
-
- if (use_packed_git(p))
- die("cannot map packed file");
- retval = unpack_entry_gently(p, entry->offset, type, sizep);
- unuse_packed_git(p);
- if (!retval)
- die("corrupted pack file %s", p->pack_name);
- return retval;
-}
-
-/* The caller is responsible for use_packed_git()/unuse_packed_git() pair */
-void *unpack_entry_gently(struct packed_git *p, unsigned long offset,
- char *type, unsigned long *sizep)
+void *unpack_entry(struct packed_git *p, off_t obj_offset,
+ enum object_type *type, unsigned long *sizep)
{
- unsigned long size, obj_offset = offset;
- enum object_type kind;
+ struct pack_window *w_curs = NULL;
+ off_t curpos = obj_offset;
+ void *data;
- offset = unpack_object_header(p, offset, &kind, &size);
- switch (kind) {
+ *type = unpack_object_header(p, &w_curs, &curpos, sizep);
+ switch (*type) {
case OBJ_OFS_DELTA:
case OBJ_REF_DELTA:
- return unpack_delta_entry(p, offset, size, kind, obj_offset, type, sizep);
+ data = unpack_delta_entry(p, &w_curs, curpos, *sizep,
+ obj_offset, type, sizep);
+ break;
case OBJ_COMMIT:
case OBJ_TREE:
case OBJ_BLOB:
case OBJ_TAG:
- strcpy(type, type_names[kind]);
- *sizep = size;
- return unpack_compressed_entry(p, offset, size);
+ data = unpack_compressed_entry(p, &w_curs, curpos, *sizep);
+ break;
default:
- return NULL;
+ die("unknown object type %i in %s", *type, p->pack_name);
}
+ unuse_pack(&w_curs);
+ return data;
}
-int num_packed_objects(const struct packed_git *p)
+uint32_t num_packed_objects(const struct packed_git *p)
{
/* See check_packed_git_idx() */
- return (p->index_size - 20 - 20 - 4*256) / 24;
+ return (uint32_t)((p->index_size - 20 - 20 - 4*256) / 24);
}
-int nth_packed_object_sha1(const struct packed_git *p, int n,
+int nth_packed_object_sha1(const struct packed_git *p, uint32_t n,
unsigned char* sha1)
{
- void *index = p->index_base + 256;
- if (n < 0 || num_packed_objects(p) <= n)
+ const unsigned char *index = p->index_data;
+ index += 4 * 256;
+ if (num_packed_objects(p) <= n)
return -1;
- hashcpy(sha1, (unsigned char *) index + (24 * n) + 4);
+ hashcpy(sha1, index + 24 * n + 4);
return 0;
}
-unsigned long find_pack_entry_one(const unsigned char *sha1,
+off_t find_pack_entry_one(const unsigned char *sha1,
struct packed_git *p)
{
- unsigned int *level1_ofs = p->index_base;
+ const uint32_t *level1_ofs = p->index_data;
int hi = ntohl(level1_ofs[*sha1]);
int lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1]));
- void *index = p->index_base + 256;
+ const unsigned char *index = p->index_data;
+
+ index += 4 * 256;
do {
int mi = (lo + hi) / 2;
- int cmp = hashcmp((unsigned char *)index + (24 * mi) + 4, sha1);
+ int cmp = hashcmp(index + 24 * mi + 4, sha1);
if (!cmp)
- return ntohl(*((unsigned int *) ((char *) index + (24 * mi))));
+ return ntohl(*((uint32_t *)((char *)index + (24 * mi))));
if (cmp > 0)
hi = mi;
else
static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e, const char **ignore_packed)
{
struct packed_git *p;
- unsigned long offset;
+ off_t offset;
prepare_packed_git();
}
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);
+ continue;
+ }
e->offset = offset;
e->p = p;
hashcpy(e->sha1, sha1);
return p;
}
return NULL;
-
+
}
-static int sha1_loose_object_info(const unsigned char *sha1, char *type, unsigned long *sizep)
+static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *sizep)
{
int status;
unsigned long mapsize, size;
void *map;
z_stream stream;
- char hdr[128];
+ char hdr[32];
map = map_sha1_file(sha1, &mapsize);
if (!map)
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)
+ else if ((status = parse_sha1_header(hdr, &size)) < 0)
status = error("unable to parse %s header", sha1_to_hex(sha1));
- else {
- status = 0;
- if (sizep)
- *sizep = size;
- }
+ else if (sizep)
+ *sizep = size;
inflateEnd(&stream);
munmap(map, mapsize);
return status;
}
-int sha1_object_info(const unsigned char *sha1, char *type, unsigned long *sizep)
+int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
{
- int status;
struct pack_entry e;
if (!find_pack_entry(sha1, &e, NULL)) {
reprepare_packed_git();
if (!find_pack_entry(sha1, &e, NULL))
- return sha1_loose_object_info(sha1, type, sizep);
+ return sha1_loose_object_info(sha1, sizep);
}
- if (use_packed_git(e.p))
- die("cannot map packed file");
- status = packed_object_info(e.p, e.offset, type, sizep);
- unuse_packed_git(e.p);
- return status;
+ return packed_object_info(e.p, e.offset, sizep);
}
-static void *read_packed_sha1(const unsigned char *sha1, char *type, unsigned long *size)
+static void *read_packed_sha1(const unsigned char *sha1,
+ enum object_type *type, unsigned long *size)
{
struct pack_entry e;
- if (!find_pack_entry(sha1, &e, NULL)) {
- error("cannot read sha1_file for %s", sha1_to_hex(sha1));
+ if (!find_pack_entry(sha1, &e, NULL))
return NULL;
+ else
+ return cache_or_unpack_entry(e.p, e.offset, size, type, 1);
+}
+
+/*
+ * 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 *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;
+ }
+ return NULL;
+}
+
+int pretend_sha1_file(void *buf, unsigned long len, enum object_type type,
+ unsigned char *sha1)
+{
+ struct cached_object *co;
+
+ hash_sha1_file(buf, len, typename(type), sha1);
+ if (has_sha1_file(sha1) || find_cached_object(sha1))
+ return 0;
+ if (cached_object_alloc <= cached_object_nr) {
+ cached_object_alloc = alloc_nr(cached_object_alloc);
+ cached_objects = xrealloc(cached_objects,
+ sizeof(*cached_objects) *
+ cached_object_alloc);
}
- return unpack_entry(&e, type, size);
+ co = &cached_objects[cached_object_nr++];
+ co->size = len;
+ co->type = type;
+ co->buf = xmalloc(len);
+ memcpy(co->buf, buf, len);
+ hashcpy(co->sha1, sha1);
+ return 0;
}
-void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size)
+void *read_sha1_file(const unsigned char *sha1, enum object_type *type,
+ unsigned long *size)
{
unsigned long mapsize;
void *map, *buf;
- struct pack_entry e;
+ struct cached_object *co;
+
+ co = find_cached_object(sha1);
+ if (co) {
+ buf = xmalloc(co->size + 1);
+ memcpy(buf, co->buf, co->size);
+ ((char*)buf)[co->size] = 0;
+ *type = co->type;
+ *size = co->size;
+ return buf;
+ }
- if (find_pack_entry(sha1, &e, NULL))
- return read_packed_sha1(sha1, type, size);
+ buf = read_packed_sha1(sha1, type, size);
+ if (buf)
+ return buf;
map = map_sha1_file(sha1, &mapsize);
if (map) {
- buf = unpack_sha1_file(map, mapsize, type, size);
+ buf = unpack_sha1_file(map, mapsize, type, size, sha1);
munmap(map, mapsize);
return buf;
}
reprepare_packed_git();
- if (find_pack_entry(sha1, &e, NULL))
- return read_packed_sha1(sha1, type, size);
- return NULL;
+ return read_packed_sha1(sha1, type, size);
}
void *read_object_with_reference(const unsigned char *sha1,
- const char *required_type,
+ const char *required_type_name,
unsigned long *size,
unsigned char *actual_sha1_return)
{
- char type[20];
+ enum object_type type, required_type;
void *buffer;
unsigned long isize;
unsigned char actual_sha1[20];
+ required_type = type_from_string(required_type_name);
hashcpy(actual_sha1, sha1);
while (1) {
int ref_length = -1;
const char *ref_type = NULL;
- buffer = read_sha1_file(actual_sha1, type, &isize);
+ buffer = read_sha1_file(actual_sha1, &type, &isize);
if (!buffer)
return NULL;
- if (!strcmp(type, required_type)) {
+ if (type == required_type) {
*size = isize;
if (actual_sha1_return)
hashcpy(actual_sha1_return, actual_sha1);
return buffer;
}
/* Handle references */
- else if (!strcmp(type, commit_type))
+ else if (type == OBJ_COMMIT)
ref_type = "tree ";
- else if (!strcmp(type, tag_type))
+ else if (type == OBJ_TAG)
ref_type = "object ";
else {
free(buffer);
}
}
-static void write_sha1_file_prepare(void *buf, unsigned long len,
+static void write_sha1_file_prepare(const void *buf, unsigned long len,
const char *type, unsigned char *sha1,
- unsigned char *hdr, int *hdrlen)
+ char *hdr, int *hdrlen)
{
SHA_CTX c;
/* Generate the header */
- *hdrlen = sprintf((char *)hdr, "%s %lu", type, len)+1;
+ *hdrlen = sprintf(hdr, "%s %lu", type, len)+1;
/* Sha1.. */
SHA1_Init(&c);
static int write_buffer(int fd, const void *buf, size_t len)
{
- while (len) {
- ssize_t size;
-
- size = write(fd, buf, len);
- if (!size)
- return error("file write: disk full");
- if (size < 0) {
- if (errno == EINTR || errno == EAGAIN)
- continue;
- return error("file write error (%s)", strerror(errno));
- }
- len -= size;
- buf = (char *) buf + size;
- }
+ if (write_in_full(fd, buf, len) < 0)
+ return error("file write error (%s)", strerror(errno));
return 0;
}
static void setup_object_header(z_stream *stream, const char *type, unsigned long len)
{
- int obj_type, hdr;
+ int obj_type, hdrlen;
if (use_legacy_headers) {
while (deflate(stream, 0) == Z_OK)
/* nothing */;
return;
}
- if (!strcmp(type, blob_type))
- obj_type = OBJ_BLOB;
- else if (!strcmp(type, tree_type))
- obj_type = OBJ_TREE;
- else if (!strcmp(type, commit_type))
- obj_type = OBJ_COMMIT;
- else if (!strcmp(type, tag_type))
- obj_type = OBJ_TAG;
- else
- die("trying to generate bogus object of type '%s'", type);
- hdr = write_binary_header(stream->next_out, obj_type, len);
- stream->total_out = hdr;
- stream->next_out += hdr;
- stream->avail_out -= hdr;
+ obj_type = type_from_string(type);
+ hdrlen = write_binary_header(stream->next_out, obj_type, len);
+ stream->total_out = hdrlen;
+ stream->next_out += hdrlen;
+ stream->avail_out -= hdrlen;
}
-int hash_sha1_file(void *buf, unsigned long len, const char *type,
+int hash_sha1_file(const void *buf, unsigned long len, const char *type,
unsigned char *sha1)
{
- unsigned char hdr[50];
+ char hdr[32];
int hdrlen;
write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen);
return 0;
int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
{
- int size;
+ int size, ret;
unsigned char *compressed;
z_stream stream;
unsigned char sha1[20];
char *filename;
static char tmpfile[PATH_MAX];
- unsigned char hdr[50];
+ char hdr[32];
int fd, hdrlen;
/* Normally if we have it in the pack then we do not bother writing
stream.avail_out = size;
/* First header.. */
- stream.next_in = hdr;
+ stream.next_in = (unsigned char *)hdr;
stream.avail_in = hdrlen;
setup_object_header(&stream, type, len);
/* Then the data itself.. */
stream.next_in = buf;
stream.avail_in = len;
- while (deflate(&stream, Z_FINISH) == Z_OK)
- /* nothing */;
- deflateEnd(&stream);
+ ret = deflate(&stream, Z_FINISH);
+ 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);
+
size = stream.total_out;
if (write_buffer(fd, compressed, size) < 0)
z_stream stream;
unsigned char *unpacked;
unsigned long len;
- char type[20];
- char hdr[50];
+ enum object_type type;
+ char hdr[32];
int hdrlen;
void *buf;
/* need to unpack and recompress it by itself */
- unpacked = read_packed_sha1(sha1, type, &len);
+ unpacked = read_packed_sha1(sha1, &type, &len);
+ if (!unpacked)
+ error("cannot read sha1_file for %s", sha1_to_hex(sha1));
- hdrlen = sprintf(hdr, "%s %lu", type, len) + 1;
+ hdrlen = sprintf(hdr, "%s %lu", typename(type), len) + 1;
/* Set it up */
memset(&stream, 0, sizeof(stream));
if (ret != Z_OK)
break;
}
- size = read(fd, buffer + *bufposn, bufsize - *bufposn);
+ size = xread(fd, buffer + *bufposn, bufsize - *bufposn);
if (size <= 0) {
close(local);
unlink(tmpfile);
return ret;
}
-int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, const char *type)
+int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
+ enum object_type type, const char *path)
{
- unsigned long size = st->st_size;
- void *buf;
- int ret;
+ size_t size = xsize_t(st->st_size);
+ void *buf = NULL;
+ int ret, re_allocated = 0;
- buf = "";
if (size)
- buf = mmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
+ buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
close(fd);
- if (buf == MAP_FAILED)
- return -1;
if (!type)
- type = blob_type;
+ type = OBJ_BLOB;
+
+ /*
+ * Convert blobs to git internal format
+ */
+ if ((type == OBJ_BLOB) && S_ISREG(st->st_mode)) {
+ unsigned long nsize = size;
+ char *nbuf = buf;
+ if (convert_to_git(path, &nbuf, &nsize)) {
+ if (size)
+ munmap(buf, size);
+ size = nsize;
+ buf = nbuf;
+ re_allocated = 1;
+ }
+ }
+
if (write_object)
- ret = write_sha1_file(buf, size, type, sha1);
+ ret = write_sha1_file(buf, size, typename(type), sha1);
else
- ret = hash_sha1_file(buf, size, type, sha1);
+ ret = hash_sha1_file(buf, size, typename(type), sha1);
+ if (re_allocated) {
+ free(buf);
+ return ret;
+ }
if (size)
munmap(buf, size);
return ret;
{
int fd;
char *target;
+ size_t len;
switch (st->st_mode & S_IFMT) {
case S_IFREG:
if (fd < 0)
return error("open(\"%s\"): %s", path,
strerror(errno));
- if (index_fd(sha1, fd, st, write_object, NULL) < 0)
+ if (index_fd(sha1, fd, st, write_object, OBJ_BLOB, path) < 0)
return error("%s: failed to insert into database",
path);
break;
case S_IFLNK:
- target = xmalloc(st->st_size+1);
- if (readlink(path, target, st->st_size+1) != st->st_size) {
+ len = xsize_t(st->st_size);
+ target = xmalloc(len + 1);
+ if (readlink(path, target, len + 1) != st->st_size) {
char *errstr = strerror(errno);
free(target);
return error("readlink(\"%s\"): %s", path,
errstr);
}
if (!write_object)
- hash_sha1_file(target, st->st_size, blob_type, sha1);
- else if (write_sha1_file(target, st->st_size, blob_type, sha1))
+ hash_sha1_file(target, len, blob_type, sha1);
+ else if (write_sha1_file(target, len, blob_type, sha1))
return error("%s: failed to insert into database",
path);
free(target);
}
return 0;
}
+
+int read_pack_header(int fd, struct pack_header *header)
+{
+ char *c = (char*)header;
+ ssize_t remaining = sizeof(struct pack_header);
+ do {
+ ssize_t r = xread(fd, c, remaining);
+ if (r <= 0)
+ /* "eof before pack header was fully read" */
+ return PH_ERROR_EOF;
+ remaining -= r;
+ c += r;
+ } while (remaining > 0);
+ if (header->hdr_signature != htonl(PACK_SIGNATURE))
+ /* "protocol error (pack signature mismatch detected)" */
+ return PH_ERROR_PACK_SIGNATURE;
+ if (!pack_version_ok(header->hdr_version))
+ /* "protocol error (pack version unsupported)" */
+ return PH_ERROR_PROTOCOL;
+ return 0;
+}