#include "tree-walk.h"
#include "tree.h"
#include "object-store.h"
+#include "midx.h"
char *odb_pack_name(struct strbuf *buf,
const unsigned char *sha1,
uint32_t version, nr, i, *index;
int fd = git_open(path);
struct stat st;
+ const unsigned int hashsz = the_hash_algo->rawsz;
if (fd < 0)
return -1;
return -1;
}
idx_size = xsize_t(st.st_size);
- if (idx_size < 4 * 256 + 20 + 20) {
+ if (idx_size < 4 * 256 + hashsz + hashsz) {
close(fd);
return error("index file %s is too small", path);
}
/*
* 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
+ * - 24-byte entries * nr (object ID + 4-byte offset)
+ * - hash of the packfile
+ * - file checksum
*/
- if (idx_size != 4*256 + nr * 24 + 20 + 20) {
+ if (idx_size != 4*256 + nr * (hashsz + 4) + hashsz + hashsz) {
munmap(idx_map, idx_size);
return error("wrong index v1 file size in %s", path);
}
* Minimum size:
* - 8 bytes of header
* - 256 index entries 4 bytes each
- * - 20-byte sha1 entry * nr
+ * - object ID entry * nr
* - 4-byte crc entry * nr
* - 4-byte offset entry * nr
- * - 20-byte SHA1 of the packfile
- * - 20-byte SHA1 file checksum
+ * - hash of the packfile
+ * - 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;
+ unsigned long min_size = 8 + 4*256 + nr*(hashsz + 4 + 4) + hashsz + hashsz;
unsigned long max_size = min_size;
if (nr)
max_size += (nr - 1)*8;
return 0;
if (!strip_suffix(p->pack_name, ".pack", &len))
- die("BUG: pack_name does not end in .pack");
+ BUG("pack_name does not end in .pack");
idx_name = xstrfmt("%.*s.idx", (int)len, p->pack_name);
ret = check_packed_git_idx(idx_name, p);
free(idx_name);
return ret;
}
+uint32_t get_pack_fanout(struct packed_git *p, uint32_t value)
+{
+ const uint32_t *level1_ofs = p->index_data;
+
+ if (!level1_ofs) {
+ if (open_pack_index(p))
+ return 0;
+ level1_ofs = p->index_data;
+ }
+
+ if (p->index_version > 1) {
+ level1_ofs += 2;
+ }
+
+ return ntohl(level1_ofs[value]);
+}
+
static struct packed_git *alloc_packed_git(int extra)
{
struct packed_git *p = xmalloc(st_add(sizeof(*p), extra));
for (p = o->packed_git; p; p = p->next)
if (p->do_not_close)
- die("BUG: want to close pack marked 'do-not-close'");
+ BUG("want to close pack marked 'do-not-close'");
else
close_pack(p);
}
{
struct stat st;
struct pack_header hdr;
- unsigned char sha1[20];
- unsigned char *idx_sha1;
+ unsigned char hash[GIT_MAX_RAWSZ];
+ unsigned char *idx_hash;
long fd_flag;
ssize_t read_result;
+ const unsigned hashsz = the_hash_algo->rawsz;
- if (!p->index_data && open_pack_index(p))
- return error("packfile %s index unavailable", p->pack_name);
+ if (!p->index_data) {
+ struct multi_pack_index *m;
+ const char *pack_name = strrchr(p->pack_name, '/');
+
+ for (m = the_repository->objects->multi_pack_index;
+ m; m = m->next) {
+ if (midx_contains_pack(m, pack_name))
+ break;
+ }
+
+ if (!m && open_pack_index(p))
+ return error("packfile %s index unavailable", p->pack_name);
+ }
if (!pack_max_fds) {
unsigned int max_fds = get_max_fd_limit();
" supported (try upgrading GIT to a newer version)",
p->pack_name, ntohl(hdr.hdr_version));
+ /* Skip index checking if in multi-pack-index */
+ if (!p->index_data)
+ return 0;
+
/* Verify the pack matches its index. */
if (p->num_objects != ntohl(hdr.hdr_entries))
return error("packfile %s claims to have %"PRIu32" objects"
" while index indicates %"PRIu32" objects",
p->pack_name, ntohl(hdr.hdr_entries),
p->num_objects);
- if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1)
+ if (lseek(p->pack_fd, p->pack_size - hashsz, SEEK_SET) == -1)
return error("end of packfile %s is unavailable", p->pack_name);
- read_result = read_in_full(p->pack_fd, sha1, sizeof(sha1));
+ read_result = read_in_full(p->pack_fd, hash, hashsz);
if (read_result < 0)
return error_errno("error reading from %s", p->pack_name);
- if (read_result != sizeof(sha1))
+ if (read_result != hashsz)
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))
+ idx_hash = ((unsigned char *)p->index_data) + p->index_size - hashsz * 2;
+ if (!hasheq(hash, idx_hash))
return error("packfile %s does not match index", p->pack_name);
return 0;
}
static int in_window(struct pack_window *win, off_t offset)
{
- /* We must promise at least 20 bytes (one hash) after the
+ /* We must promise at least one full 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
*/
off_t win_off = win->offset;
return win_off <= offset
- && (offset + 20) <= (win_off + win->len);
+ && (offset + the_hash_algo->rawsz) <= (win_off + win->len);
}
unsigned char *use_pack(struct packed_git *p,
*/
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))
+ if (offset > (p->pack_size - the_hash_algo->rawsz))
die("offset beyond end of packfile (truncated pack?)");
if (offset < 0)
die(_("offset before end of packfile (broken .idx?)"));
p->pack_size = st.st_size;
p->pack_local = local;
p->mtime = st.st_mtime;
- if (path_len < 40 || get_sha1_hex(path + path_len - 40, p->sha1))
+ if (path_len < the_hash_algo->hexsz ||
+ get_sha1_hex(path + path_len - the_hash_algo->hexsz, p->sha1))
hashclr(p->sha1);
return p;
}
report_helper(list, seen_bits, first, list->nr);
}
-static void prepare_packed_git_one(struct repository *r, char *objdir, int local)
+void for_each_file_in_pack_dir(const char *objdir,
+ each_file_in_pack_dir_fn fn,
+ void *data)
{
struct strbuf path = STRBUF_INIT;
size_t dirnamelen;
DIR *dir;
struct dirent *de;
- struct string_list garbage = STRING_LIST_INIT_DUP;
strbuf_addstr(&path, objdir);
strbuf_addstr(&path, "/pack");
strbuf_addch(&path, '/');
dirnamelen = path.len;
while ((de = readdir(dir)) != NULL) {
- struct packed_git *p;
- size_t base_len;
-
if (is_dot_or_dotdot(de->d_name))
continue;
strbuf_setlen(&path, dirnamelen);
strbuf_addstr(&path, de->d_name);
- base_len = path.len;
- if (strip_suffix_mem(path.buf, &base_len, ".idx")) {
- /* Don't reopen a pack we already have. */
- for (p = r->objects->packed_git; p;
- p = p->next) {
- size_t len;
- if (strip_suffix(p->pack_name, ".pack", &len) &&
- len == base_len &&
- !memcmp(p->pack_name, path.buf, len))
- break;
- }
- if (p == NULL &&
- /*
- * See if it really is a valid .idx file with
- * corresponding .pack file that we can map.
- */
- (p = add_packed_git(path.buf, path.len, local)) != NULL)
- install_packed_git(r, p);
- }
-
- if (!report_garbage)
- continue;
-
- if (ends_with(de->d_name, ".idx") ||
- ends_with(de->d_name, ".pack") ||
- ends_with(de->d_name, ".bitmap") ||
- ends_with(de->d_name, ".keep") ||
- ends_with(de->d_name, ".promisor"))
- string_list_append(&garbage, path.buf);
- else
- report_garbage(PACKDIR_FILE_GARBAGE, path.buf);
+ fn(path.buf, path.len, de->d_name, data);
}
+
closedir(dir);
- report_pack_garbage(&garbage);
- string_list_clear(&garbage, 0);
strbuf_release(&path);
}
+struct prepare_pack_data {
+ struct repository *r;
+ struct string_list *garbage;
+ int local;
+ struct multi_pack_index *m;
+};
+
+static void prepare_pack(const char *full_name, size_t full_name_len,
+ const char *file_name, void *_data)
+{
+ struct prepare_pack_data *data = (struct prepare_pack_data *)_data;
+ struct packed_git *p;
+ size_t base_len = full_name_len;
+
+ if (strip_suffix_mem(full_name, &base_len, ".idx") &&
+ !(data->m && midx_contains_pack(data->m, file_name))) {
+ /* Don't reopen a pack we already have. */
+ for (p = data->r->objects->packed_git; p; p = p->next) {
+ size_t len;
+ if (strip_suffix(p->pack_name, ".pack", &len) &&
+ len == base_len &&
+ !memcmp(p->pack_name, full_name, len))
+ break;
+ }
+
+ if (!p) {
+ p = add_packed_git(full_name, full_name_len, data->local);
+ if (p)
+ install_packed_git(data->r, p);
+ }
+ }
+
+ if (!report_garbage)
+ return;
+
+ if (!strcmp(file_name, "multi-pack-index"))
+ return;
+ if (ends_with(file_name, ".idx") ||
+ ends_with(file_name, ".pack") ||
+ ends_with(file_name, ".bitmap") ||
+ ends_with(file_name, ".keep") ||
+ ends_with(file_name, ".promisor"))
+ string_list_append(data->garbage, full_name);
+ else
+ report_garbage(PACKDIR_FILE_GARBAGE, full_name);
+}
+
+static void prepare_packed_git_one(struct repository *r, char *objdir, int local)
+{
+ struct prepare_pack_data data;
+ struct string_list garbage = STRING_LIST_INIT_DUP;
+
+ data.m = r->objects->multi_pack_index;
+
+ /* look for the multi-pack-index for this object directory */
+ while (data.m && strcmp(data.m->object_dir, objdir))
+ data.m = data.m->next;
+
+ data.r = r;
+ data.garbage = &garbage;
+ data.local = local;
+
+ for_each_file_in_pack_dir(objdir, prepare_pack, &data);
+
+ report_pack_garbage(data.garbage);
+ string_list_clear(data.garbage, 0);
+}
+
static void prepare_packed_git(struct repository *r);
/*
* Give a fast, rough count of the number of objects in the repository. This
{
if (!the_repository->objects->approximate_object_count_valid) {
unsigned long count;
+ struct multi_pack_index *m;
struct packed_git *p;
prepare_packed_git(the_repository);
count = 0;
+ for (m = get_multi_pack_index(the_repository); m; m = m->next)
+ count += m->num_objects;
for (p = the_repository->objects->packed_git; p; p = p->next) {
if (open_pack_index(p))
continue;
if (r->objects->packed_git_initialized)
return;
+ prepare_multi_pack_index_one(r, r->objects->objectdir, 1);
prepare_packed_git_one(r, r->objects->objectdir, 1);
prepare_alt_odb(r);
- for (alt = r->objects->alt_odb_list; alt; alt = alt->next)
+ for (alt = r->objects->alt_odb_list; alt; alt = alt->next) {
+ prepare_multi_pack_index_one(r, alt->path, 0);
prepare_packed_git_one(r, alt->path, 0);
+ }
rearrange_packed_git(r);
+
+ r->objects->all_packs = NULL;
+
prepare_packed_git_mru(r);
r->objects->packed_git_initialized = 1;
}
return r->objects->packed_git;
}
+struct multi_pack_index *get_multi_pack_index(struct repository *r)
+{
+ prepare_packed_git(r);
+ return r->objects->multi_pack_index;
+}
+
+struct packed_git *get_all_packs(struct repository *r)
+{
+ prepare_packed_git(r);
+
+ if (!r->objects->all_packs) {
+ struct packed_git *p = r->objects->packed_git;
+ struct multi_pack_index *m;
+
+ for (m = r->objects->multi_pack_index; m; m = m->next) {
+ uint32_t i;
+ for (i = 0; i < m->num_packs; i++) {
+ if (!prepare_midx_pack(m, i)) {
+ m->packs[i]->next = p;
+ p = m->packs[i];
+ }
+ }
+ }
+
+ r->objects->all_packs = p;
+ }
+
+ return r->objects->all_packs;
+}
+
struct list_head *get_packed_git_mru(struct repository *r)
{
prepare_packed_git(r);
{
unsigned i;
for (i = 0; i < p->num_bad_objects; i++)
- if (!hashcmp(sha1, p->bad_object_sha1 + GIT_SHA1_RAWSZ * i))
+ if (hasheq(sha1, p->bad_object_sha1 + GIT_SHA1_RAWSZ * i))
return;
p->bad_object_sha1 = xrealloc(p->bad_object_sha1,
st_mult(GIT_MAX_RAWSZ,
for (p = the_repository->objects->packed_git; p; p = p->next)
for (i = 0; i < p->num_bad_objects; i++)
- if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
+ if (hasheq(sha1,
+ p->bad_object_sha1 + the_hash_algo->rawsz * i))
return p;
return NULL;
}
} else if (type == OBJ_REF_DELTA) {
/* The base entry _must_ be in the same pack */
base_offset = find_pack_entry_one(base_info, p);
- *curpos += 20;
+ *curpos += the_hash_algo->rawsz;
} else
die("I am totally screwed");
return base_offset;
return NULL;
}
-static int retry_bad_packed_offset(struct packed_git *p, off_t obj_offset)
+static int retry_bad_packed_offset(struct repository *r,
+ struct packed_git *p,
+ off_t obj_offset)
{
int type;
struct revindex_entry *revidx;
return OBJ_BAD;
nth_packed_object_oid(&oid, p, revidx->nr);
mark_bad_packed_object(p, oid.hash);
- type = oid_object_info(&oid, NULL);
+ type = oid_object_info(r, &oid, NULL);
if (type <= OBJ_NONE)
return OBJ_BAD;
return type;
#define POI_STACK_PREALLOC 64
-static enum object_type packed_to_object_type(struct packed_git *p,
+static enum object_type packed_to_object_type(struct repository *r,
+ struct packed_git *p,
off_t obj_offset,
enum object_type type,
struct pack_window **w_curs,
if (type <= OBJ_NONE) {
/* If getting the base itself fails, we first
* retry the base, otherwise unwind */
- type = retry_bad_packed_offset(p, base_offset);
+ type = retry_bad_packed_offset(r, p, base_offset);
if (type > OBJ_NONE)
goto out;
goto unwind;
unwind:
while (poi_stack_nr) {
obj_offset = poi_stack[--poi_stack_nr];
- type = retry_bad_packed_offset(p, obj_offset);
+ type = retry_bad_packed_offset(r, p, obj_offset);
if (type > OBJ_NONE)
goto out;
}
free(ent);
}
-static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset,
- unsigned long *base_size, enum object_type *type)
+static void *cache_or_unpack_entry(struct repository *r, struct packed_git *p,
+ off_t base_offset, unsigned long *base_size,
+ enum object_type *type)
{
struct delta_base_cache_entry *ent;
ent = get_delta_base_cache_entry(p, base_offset);
if (!ent)
- return unpack_entry(p, base_offset, type, base_size);
+ return unpack_entry(r, p, base_offset, type, base_size);
if (type)
*type = ent->type;
hashmap_add(&delta_base_cache, ent);
}
-int packed_object_info(struct packed_git *p, off_t obj_offset,
- struct object_info *oi)
+int packed_object_info(struct repository *r, struct packed_git *p,
+ off_t obj_offset, struct object_info *oi)
{
struct pack_window *w_curs = NULL;
unsigned long size;
* a "real" type later if the caller is interested.
*/
if (oi->contentp) {
- *oi->contentp = cache_or_unpack_entry(p, obj_offset, oi->sizep,
+ *oi->contentp = cache_or_unpack_entry(r, p, obj_offset, oi->sizep,
&type);
if (!*oi->contentp)
type = OBJ_BAD;
if (oi->typep || oi->type_name) {
enum object_type ptot;
- ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
- curpos);
+ ptot = packed_to_object_type(r, p, obj_offset,
+ type, &w_curs, curpos);
if (oi->typep)
*oi->typep = ptot;
if (oi->type_name) {
return NULL;
}
+ /* versions of zlib can clobber unconsumed portion of outbuf */
+ buffer[size] = '\0';
+
return buffer;
}
unsigned long size;
};
-static void *read_object(const struct object_id *oid, enum object_type *type,
+static void *read_object(struct repository *r,
+ const struct object_id *oid,
+ enum object_type *type,
unsigned long *size)
{
struct object_info oi = OBJECT_INFO_INIT;
oi.sizep = size;
oi.contentp = &content;
- if (oid_object_info_extended(oid, &oi, 0) < 0)
+ if (oid_object_info_extended(r, oid, &oi, 0) < 0)
return NULL;
return content;
}
-void *unpack_entry(struct packed_git *p, off_t obj_offset,
+void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset,
enum object_type *final_type, unsigned long *final_size)
{
struct pack_window *w_curs = NULL;
case OBJ_OFS_DELTA:
case OBJ_REF_DELTA:
if (data)
- die("BUG: unpack_entry: left loop at a valid delta");
+ BUG("unpack_entry: left loop at a valid delta");
break;
case OBJ_COMMIT:
case OBJ_TREE:
oid_to_hex(&base_oid), (uintmax_t)obj_offset,
p->pack_name);
mark_bad_packed_object(p, base_oid.hash);
- base = read_object(&base_oid, &type, &base_size);
+ base = read_object(r, &base_oid, &type, &base_size);
external_base = base;
}
}
{
const unsigned char *index_fanout = p->index_data;
const unsigned char *index_lookup;
+ const unsigned int hashsz = the_hash_algo->rawsz;
int index_lookup_width;
if (!index_fanout)
index_lookup = index_fanout + 4 * 256;
if (p->index_version == 1) {
- index_lookup_width = 24;
+ index_lookup_width = hashsz + 4;
index_lookup += 4;
} else {
- index_lookup_width = 20;
+ index_lookup_width = hashsz;
index_fanout += 8;
index_lookup += 8;
}
uint32_t n)
{
const unsigned char *index = p->index_data;
+ const unsigned int hashsz = the_hash_algo->rawsz;
if (!index) {
if (open_pack_index(p))
return NULL;
return NULL;
index += 4 * 256;
if (p->index_version == 1) {
- return index + 24 * n + 4;
+ return index + (hashsz + 4) * n + 4;
} else {
index += 8;
- return index + 20 * n;
+ return index + hashsz * n;
}
}
off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n)
{
const unsigned char *index = p->index_data;
+ const unsigned int hashsz = the_hash_algo->rawsz;
index += 4 * 256;
if (p->index_version == 1) {
- return ntohl(*((uint32_t *)(index + 24 * n)));
+ return ntohl(*((uint32_t *)(index + (hashsz + 4) * n)));
} else {
uint32_t off;
- index += 8 + p->num_objects * (20 + 4);
+ index += 8 + p->num_objects * (hashsz + 4);
off = ntohl(*((uint32_t *)(index + 4 * n)));
if (!(off & 0x80000000))
return off;
}
-static int fill_pack_entry(const unsigned char *sha1,
+static int fill_pack_entry(const struct object_id *oid,
struct pack_entry *e,
struct packed_git *p)
{
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))
+ if (hasheq(oid->hash,
+ p->bad_object_sha1 + the_hash_algo->rawsz * i))
return 0;
}
- offset = find_pack_entry_one(sha1, p);
+ offset = find_pack_entry_one(oid->hash, p);
if (!offset)
return 0;
return 0;
e->offset = offset;
e->p = p;
- hashcpy(e->sha1, sha1);
return 1;
}
-int find_pack_entry(struct repository *r, const unsigned char *sha1, struct pack_entry *e)
+int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e)
{
struct list_head *pos;
+ struct multi_pack_index *m;
prepare_packed_git(r);
- if (!r->objects->packed_git)
+ if (!r->objects->packed_git && !r->objects->multi_pack_index)
return 0;
+ for (m = r->objects->multi_pack_index; m; m = m->next) {
+ if (fill_midx_entry(oid, e, m))
+ return 1;
+ }
+
list_for_each(pos, &r->objects->packed_git_mru) {
struct packed_git *p = list_entry(pos, struct packed_git, mru);
- if (fill_pack_entry(sha1, e, p)) {
+ if (fill_pack_entry(oid, e, p)) {
list_move(&p->mru, &r->objects->packed_git_mru);
return 1;
}
return 0;
}
-int has_sha1_pack(const unsigned char *sha1)
+int has_object_pack(const struct object_id *oid)
{
struct pack_entry e;
- return find_pack_entry(the_repository, sha1, &e);
+ return find_pack_entry(the_repository, oid, &e);
}
int has_pack_index(const unsigned char *sha1)
return 1;
}
-int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn cb, void *data)
+int for_each_object_in_pack(struct packed_git *p,
+ each_packed_object_fn cb, void *data,
+ enum for_each_object_flags flags)
{
uint32_t i;
int r = 0;
+ if (flags & FOR_EACH_OBJECT_PACK_ORDER)
+ load_pack_revindex(p);
+
for (i = 0; i < p->num_objects; i++) {
+ uint32_t pos;
struct object_id oid;
- if (!nth_packed_object_oid(&oid, p, i))
+ if (flags & FOR_EACH_OBJECT_PACK_ORDER)
+ pos = p->revindex[i].nr;
+ else
+ pos = i;
+
+ if (!nth_packed_object_oid(&oid, p, pos))
return error("unable to get sha1 of object %u in %s",
- i, p->pack_name);
+ pos, p->pack_name);
- r = cb(&oid, p, i, data);
+ r = cb(&oid, p, pos, data);
if (r)
break;
}
return r;
}
-int for_each_packed_object(each_packed_object_fn cb, void *data, unsigned flags)
+int for_each_packed_object(each_packed_object_fn cb, void *data,
+ enum for_each_object_flags flags)
{
struct packed_git *p;
int r = 0;
int pack_errors = 0;
prepare_packed_git(the_repository);
- for (p = the_repository->objects->packed_git; p; p = p->next) {
+ for (p = get_all_packs(the_repository); p; p = p->next) {
if ((flags & FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local)
continue;
if ((flags & FOR_EACH_OBJECT_PROMISOR_ONLY) &&
pack_errors = 1;
continue;
}
- r = for_each_object_in_pack(p, cb, data);
+ r = for_each_object_in_pack(p, cb, data, flags);
if (r)
break;
}
void *set_)
{
struct oidset *set = set_;
- struct object *obj = parse_object(oid);
+ struct object *obj = parse_object(the_repository, oid);
if (!obj)
return 1;
struct commit *commit = (struct commit *) obj;
struct commit_list *parents = commit->parents;
- oidset_insert(set, &commit->tree->object.oid);
+ oidset_insert(set, get_commit_tree_oid(commit));
for (; parents; parents = parents->next)
oidset_insert(set, &parents->item->object.oid);
} else if (obj->type == OBJ_TAG) {