#include "commit.h"
#include "tag.h"
#include "tree.h"
+#include "refs.h"
#ifndef O_NOATIME
#if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
*buf++ = hex[val >> 4];
*buf++ = hex[val & 0xf];
}
-
+
return base;
}
*buf++ = hex[val >> 4];
*buf++ = hex[val & 0xf];
}
-
+
return base;
}
{
const char *alt;
+ if (alt_odb_tail)
+ return;
+
alt = getenv(ALTERNATE_DB_ENVIRONMENT);
if (!alt) alt = "";
- if (alt_odb_tail)
- return;
alt_odb_tail = &alt_odb_list;
link_alt_odb_entries(alt, alt + strlen(alt), ':', NULL, 0);
void *idx_map;
struct pack_idx_header *hdr;
size_t idx_size;
- uint32_t nr, i, *index;
+ uint32_t version, nr, i, *index;
int fd = open(path, O_RDONLY);
struct stat st;
idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0);
close(fd);
- /* 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);
- }
+ version = ntohl(hdr->idx_version);
+ if (version < 2 || version > 2) {
+ munmap(idx_map, idx_size);
+ return error("index file %s is version %d"
+ " and is not supported by this binary"
+ " (try upgrading GIT to a newer version)",
+ path, version);
+ }
+ } else
+ version = 1;
nr = 0;
index = idx_map;
+ if (version > 1)
+ index += 2; /* skip index header */
for (i = 0; i < 256; i++) {
uint32_t n = ntohl(index[i]);
if (n < nr) {
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) {
- munmap(idx_map, idx_size);
- return error("wrong index file size in %s", path);
+ if (version == 1) {
+ /*
+ * 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) {
+ munmap(idx_map, idx_size);
+ return error("wrong index file size in %s", path);
+ }
+ } else if (version == 2) {
+ /*
+ * Minimum size:
+ * - 8 bytes of header
+ * - 256 index entries 4 bytes each
+ * - 20-byte sha1 entry * nr
+ * - 4-byte crc entry * nr
+ * - 4-byte offset entry * nr
+ * - 20-byte SHA1 of the packfile
+ * - 20-byte SHA1 file checksum
+ * And after the 4-byte offset table might be a
+ * variable sized table containing 8-byte entries
+ * for offsets larger than 2^31.
+ */
+ unsigned long min_size = 8 + 4*256 + nr*(20 + 4 + 4) + 20 + 20;
+ if (idx_size < min_size || idx_size > min_size + (nr - 1)*8) {
+ munmap(idx_map, idx_size);
+ return error("wrong index file size in %s", path);
+ }
+ if (idx_size != min_size) {
+ /* make sure we can deal with large pack offsets */
+ off_t x = 0x7fffffffUL, y = 0xffffffffUL;
+ if (x > (x + 1) || y > (y + 1)) {
+ munmap(idx_map, idx_size);
+ return error("pack too large for current definition of off_t in %s", path);
+ }
+ }
}
- p->index_version = 1;
+ p->index_version = version;
p->index_data = idx_map;
p->index_size = idx_size;
+ p->num_objects = nr;
return 0;
}
+int open_pack_index(struct packed_git *p)
+{
+ char *idx_name;
+ int ret;
+
+ if (p->index_data)
+ return 0;
+
+ idx_name = xstrdup(p->pack_name);
+ strcpy(idx_name + strlen(idx_name) - strlen(".pack"), ".idx");
+ ret = check_packed_git_idx(idx_name, p);
+ free(idx_name);
+ return ret;
+}
+
static void scan_windows(struct packed_git *p,
struct packed_git **lru_p,
struct pack_window **lru_w,
unsigned char *idx_sha1;
long fd_flag;
+ if (!p->index_data && open_pack_index(p))
+ return error("packfile %s index unavailable", p->pack_name);
+
p->pack_fd = open(p->pack_name, O_RDONLY);
if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
return -1;
p->pack_name, ntohl(hdr.hdr_version));
/* Verify the pack matches its index. */
- if (num_packed_objects(p) != ntohl(hdr.hdr_entries))
+ if (p->num_objects != 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));
+ " while index indicates %u objects",
+ p->pack_name, ntohl(hdr.hdr_entries),
+ p->num_objects);
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 NULL;
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)) {
+ if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) {
free(p);
return NULL;
}
/* ok, it looks sane as far as we can check without
* actually mapping the pack file.
*/
+ p->index_version = 0;
+ p->index_data = NULL;
+ p->index_size = 0;
+ p->num_objects = 0;
p->pack_size = st.st_size;
p->next = NULL;
p->windows = NULL;
return map;
}
-int legacy_loose_object(unsigned char *map)
+static int legacy_loose_object(unsigned char *map)
{
unsigned int word;
return inflate(stream, 0);
}
+
+ /*
+ * 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_gently(map, mapsize, &type, &size);
if (!used || !valid_loose_object_type[type])
return -1;
unsigned long size;
/*
- * The type can be at most ten bytes (including the
+ * The type can be at most ten bytes (including the
* terminating '\0' that we add), and is followed by
* a space.
*/
return unpack_sha1_rest(&stream, hdr, *size, sha1);
}
+unsigned long get_size_from_delta(struct packed_git *p,
+ struct pack_window **w_curs,
+ off_t curpos)
+{
+ const unsigned char *data;
+ unsigned char delta_head[20], *in;
+ z_stream stream;
+ int st;
+
+ memset(&stream, 0, sizeof(stream));
+ stream.next_out = delta_head;
+ stream.avail_out = sizeof(delta_head);
+
+ inflateInit(&stream);
+ 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))
+ die("delta data unpack-initial failed");
+
+ /* Examine the initial part of the delta to figure out
+ * the result size.
+ */
+ data = delta_head;
+
+ /* ignore base size */
+ get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
+
+ /* Read the result size */
+ return get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
+}
+
static off_t get_delta_base(struct packed_git *p,
struct pack_window **w_curs,
off_t *curpos,
base_offset = c & 127;
while (c & 128) {
base_offset += 1;
- if (!base_offset || base_offset & ~(~0UL >> 7))
+ if (!base_offset || MSB(base_offset, 7))
die("offset value overflow for delta base object");
c = base_info[used++];
base_offset = (base_offset << 7) + (c & 127);
* based on a base with a wrong size. This saves tons of
* inflate() calls.
*/
- if (sizep) {
- const unsigned char *data;
- unsigned char delta_head[20], *in;
- z_stream stream;
- int st;
-
- memset(&stream, 0, sizeof(stream));
- stream.next_out = delta_head;
- stream.avail_out = sizeof(delta_head);
-
- inflateInit(&stream);
- 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))
- die("delta data unpack-initial failed");
-
- /* Examine the initial part of the delta to figure out
- * the result size.
- */
- data = delta_head;
-
- /* ignore base size */
- get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
-
- /* Read the result size */
- *sizep = get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
- }
+ if (sizep)
+ *sizep = get_size_from_delta(p, w_curs, curpos);
return type;
}
return data;
}
-uint32_t num_packed_objects(const struct packed_git *p)
+const unsigned char *nth_packed_object_sha1(struct packed_git *p,
+ uint32_t n)
{
- /* See check_packed_git_idx() */
- return (uint32_t)((p->index_size - 20 - 20 - 4*256) / 24);
+ const unsigned char *index = p->index_data;
+ if (!index) {
+ if (open_pack_index(p))
+ return NULL;
+ index = p->index_data;
+ }
+ if (n >= p->num_objects)
+ return NULL;
+ index += 4 * 256;
+ if (p->index_version == 1) {
+ return index + 24 * n + 4;
+ } else {
+ index += 8;
+ return index + 20 * n;
+ }
}
-int nth_packed_object_sha1(const struct packed_git *p, uint32_t n,
- unsigned char* sha1)
+static off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n)
{
const unsigned char *index = p->index_data;
index += 4 * 256;
- if (num_packed_objects(p) <= n)
- return -1;
- hashcpy(sha1, index + 24 * n + 4);
- return 0;
+ if (p->index_version == 1) {
+ return ntohl(*((uint32_t *)(index + 24 * n)));
+ } else {
+ uint32_t off;
+ index += 8 + p->num_objects * (20 + 4);
+ off = ntohl(*((uint32_t *)(index + 4 * n)));
+ if (!(off & 0x80000000))
+ return off;
+ index += p->num_objects * 4 + (off & 0x7fffffff) * 8;
+ return (((uint64_t)ntohl(*((uint32_t *)(index + 0)))) << 32) |
+ ntohl(*((uint32_t *)(index + 4)));
+ }
}
off_t find_pack_entry_one(const unsigned char *sha1,
struct packed_git *p)
{
const uint32_t *level1_ofs = p->index_data;
- int hi = ntohl(level1_ofs[*sha1]);
- int lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1]));
const unsigned char *index = p->index_data;
+ unsigned hi, lo;
+ if (!index) {
+ if (open_pack_index(p))
+ return 0;
+ level1_ofs = p->index_data;
+ index = p->index_data;
+ }
+ if (p->index_version > 1) {
+ level1_ofs += 2;
+ index += 8;
+ }
index += 4 * 256;
+ hi = ntohl(level1_ofs[*sha1]);
+ lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1]));
do {
- int mi = (lo + hi) / 2;
- int cmp = hashcmp(index + 24 * mi + 4, sha1);
+ unsigned mi = (lo + hi) / 2;
+ unsigned x = (p->index_version > 1) ? (mi * 20) : (mi * 24 + 4);
+ int cmp = hashcmp(index + x, sha1);
if (!cmp)
- return ntohl(*((uint32_t *)((char *)index + (24 * mi))));
+ return nth_packed_object_offset(p, mi);
if (cmp > 0)
hi = mi;
else
static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e, const char **ignore_packed)
{
+ 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;
- for (p = packed_git; p; p = p->next) {
+ do {
if (ignore_packed) {
const char **ig;
for (ig = ignore_packed; *ig; ig++)
if (!matches_pack_name(p, *ig))
break;
if (*ig)
- continue;
+ goto next;
}
+
offset = find_pack_entry_one(sha1, p);
if (offset) {
/*
*/
if (p->pack_fd == -1 && open_packed_git(p)) {
error("packfile %s cannot be accessed", p->pack_name);
- continue;
+ goto next;
}
e->offset = offset;
e->p = p;
hashcpy(e->sha1, sha1);
+ last_found = p;
return 1;
}
- }
+
+ next:
+ if (p == last_found)
+ p = packed_git;
+ else
+ p = p->next;
+ if (p == last_found)
+ p = p->next;
+ } while (p);
return 0;
}
-struct packed_git *find_sha1_pack(const unsigned char *sha1,
+struct packed_git *find_sha1_pack(const unsigned char *sha1,
struct packed_git *packs)
{
struct packed_git *p;
return 0;
}
-static int write_binary_header(unsigned char *hdr, enum object_type type, unsigned long len)
-{
- int hdr_len;
- unsigned char c;
-
- c = (type << 4) | (len & 15);
- len >>= 4;
- hdr_len = 1;
- while (len) {
- *hdr++ = c | 0x80;
- hdr_len++;
- c = (len & 0x7f);
- len >>= 7;
- }
- *hdr = c;
- return hdr_len;
-}
-
-static void setup_object_header(z_stream *stream, const char *type, unsigned long len)
-{
- int obj_type, hdrlen;
-
- if (use_legacy_headers) {
- while (deflate(stream, 0) == Z_OK)
- /* nothing */;
- return;
- }
- 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(const void *buf, unsigned long len, const char *type,
unsigned char *sha1)
{
/* First header.. */
stream.next_in = (unsigned char *)hdr;
stream.avail_in = hdrlen;
- setup_object_header(&stream, type, len);
+ while (deflate(&stream, 0) == Z_OK)
+ /* nothing */;
/* Then the data itself.. */
stream.next_in = buf;
{
char* buf = *return_buf;
unsigned long size = *return_size;
- int iret;
+ ssize_t iret;
unsigned long off = 0;
do {
*/
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);
+ char *nbuf = convert_to_git(path, buf, &nsize);
+ if (nbuf) {
+ munmap(buf, size);
size = nsize;
buf = nbuf;
re_allocated = 1;
path);
free(target);
break;
+ case S_IFDIR:
+ return resolve_gitlink_ref(path, "HEAD", sha1);
default:
return error("%s: unsupported file type", path);
}