#include "cache.h"
#include "mru.h"
#include "pack.h"
+#include "dir.h"
+#include "mergesort.h"
+#include "packfile.h"
+#include "delta.h"
+#include "list.h"
+#include "streaming.h"
+#include "sha1-lookup.h"
char *odb_pack_name(struct strbuf *buf,
const unsigned char *sha1,
static unsigned int pack_mmap_calls;
static unsigned int peak_pack_open_windows;
static unsigned int pack_open_windows;
-unsigned int pack_open_fds;
+static unsigned int pack_open_fds;
static unsigned int pack_max_fds;
static size_t peak_pack_mapped;
static size_t pack_mapped;
return 0;
}
-int open_packed_git(struct packed_git *p)
+static int open_packed_git(struct packed_git *p)
{
if (!open_packed_git_1(p))
return 0;
hashclr(p->sha1);
return p;
}
+
+void install_packed_git(struct packed_git *pack)
+{
+ if (pack->pack_fd != -1)
+ pack_open_fds++;
+
+ pack->next = packed_git;
+ packed_git = pack;
+}
+
+void (*report_garbage)(unsigned seen_bits, const char *path);
+
+static void report_helper(const struct string_list *list,
+ int seen_bits, int first, int last)
+{
+ if (seen_bits == (PACKDIR_FILE_PACK|PACKDIR_FILE_IDX))
+ return;
+
+ for (; first < last; first++)
+ report_garbage(seen_bits, list->items[first].string);
+}
+
+static void report_pack_garbage(struct string_list *list)
+{
+ int i, baselen = -1, first = 0, seen_bits = 0;
+
+ if (!report_garbage)
+ return;
+
+ string_list_sort(list);
+
+ for (i = 0; i < list->nr; i++) {
+ const char *path = list->items[i].string;
+ if (baselen != -1 &&
+ strncmp(path, list->items[first].string, baselen)) {
+ report_helper(list, seen_bits, first, i);
+ baselen = -1;
+ seen_bits = 0;
+ }
+ if (baselen == -1) {
+ const char *dot = strrchr(path, '.');
+ if (!dot) {
+ report_garbage(PACKDIR_FILE_GARBAGE, path);
+ continue;
+ }
+ baselen = dot - path + 1;
+ first = i;
+ }
+ if (!strcmp(path + baselen, "pack"))
+ seen_bits |= 1;
+ else if (!strcmp(path + baselen, "idx"))
+ seen_bits |= 2;
+ }
+ report_helper(list, seen_bits, first, list->nr);
+}
+
+static void prepare_packed_git_one(char *objdir, int local)
+{
+ 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");
+ dir = opendir(path.buf);
+ if (!dir) {
+ if (errno != ENOENT)
+ error_errno("unable to open object pack directory: %s",
+ path.buf);
+ strbuf_release(&path);
+ return;
+ }
+ 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 = 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(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"))
+ string_list_append(&garbage, path.buf);
+ else
+ report_garbage(PACKDIR_FILE_GARBAGE, path.buf);
+ }
+ closedir(dir);
+ report_pack_garbage(&garbage);
+ string_list_clear(&garbage, 0);
+ strbuf_release(&path);
+}
+
+static int approximate_object_count_valid;
+
+/*
+ * Give a fast, rough count of the number of objects in the repository. This
+ * ignores loose objects completely. If you have a lot of them, then either
+ * you should repack because your performance will be awful, or they are
+ * all unreachable objects about to be pruned, in which case they're not really
+ * interesting as a measure of repo size in the first place.
+ */
+unsigned long approximate_object_count(void)
+{
+ static unsigned long count;
+ if (!approximate_object_count_valid) {
+ struct packed_git *p;
+
+ prepare_packed_git();
+ count = 0;
+ for (p = packed_git; p; p = p->next) {
+ if (open_pack_index(p))
+ continue;
+ count += p->num_objects;
+ }
+ }
+ return count;
+}
+
+static void *get_next_packed_git(const void *p)
+{
+ return ((const struct packed_git *)p)->next;
+}
+
+static void set_next_packed_git(void *p, void *next)
+{
+ ((struct packed_git *)p)->next = next;
+}
+
+static int sort_pack(const void *a_, const void *b_)
+{
+ const struct packed_git *a = a_;
+ const struct packed_git *b = 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)
+{
+ packed_git = llist_mergesort(packed_git, get_next_packed_git,
+ set_next_packed_git, sort_pack);
+}
+
+static void prepare_packed_git_mru(void)
+{
+ struct packed_git *p;
+
+ mru_clear(packed_git_mru);
+ for (p = packed_git; p; p = p->next)
+ mru_append(packed_git_mru, p);
+}
+
+static int prepare_packed_git_run_once = 0;
+void prepare_packed_git(void)
+{
+ struct alternate_object_database *alt;
+
+ if (prepare_packed_git_run_once)
+ return;
+ prepare_packed_git_one(get_object_directory(), 1);
+ prepare_alt_odb();
+ for (alt = alt_odb_list; alt; alt = alt->next)
+ prepare_packed_git_one(alt->path, 0);
+ rearrange_packed_git();
+ prepare_packed_git_mru();
+ prepare_packed_git_run_once = 1;
+}
+
+void reprepare_packed_git(void)
+{
+ approximate_object_count_valid = 0;
+ prepare_packed_git_run_once = 0;
+ prepare_packed_git();
+}
+
+unsigned long unpack_object_header_buffer(const unsigned char *buf,
+ unsigned long len, enum object_type *type, unsigned long *sizep)
+{
+ unsigned shift;
+ unsigned long size, c;
+ unsigned long used = 0;
+
+ c = buf[used++];
+ *type = (c >> 4) & 7;
+ size = c & 15;
+ shift = 4;
+ while (c & 0x80) {
+ if (len <= used || bitsizeof(long) <= shift) {
+ error("bad object header");
+ size = used = 0;
+ break;
+ }
+ c = buf[used++];
+ size += (c & 0x7f) << shift;
+ shift += 7;
+ }
+ *sizep = size;
+ return used;
+}
+
+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;
+ git_zstream stream;
+ int st;
+
+ memset(&stream, 0, sizeof(stream));
+ stream.next_out = delta_head;
+ stream.avail_out = sizeof(delta_head);
+
+ git_inflate_init(&stream);
+ do {
+ in = use_pack(p, w_curs, curpos, &stream.avail_in);
+ stream.next_in = in;
+ st = git_inflate(&stream, Z_FINISH);
+ curpos += stream.next_in - in;
+ } while ((st == Z_OK || st == Z_BUF_ERROR) &&
+ stream.total_out < sizeof(delta_head));
+ git_inflate_end(&stream);
+ if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) {
+ error("delta data unpack-initial failed");
+ return 0;
+ }
+
+ /* 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));
+}
+
+int unpack_object_header(struct packed_git *p,
+ struct pack_window **w_curs,
+ off_t *curpos,
+ unsigned long *sizep)
+{
+ unsigned char *base;
+ unsigned long left;
+ unsigned long used;
+ enum object_type type;
+
+ /* use_pack() assures us we have [base, base + 20) available
+ * as a range that we can look at. (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_buffer(base, left, &type, sizep);
+ if (!used) {
+ type = OBJ_BAD;
+ } else
+ *curpos += used;
+
+ return type;
+}
+
+void mark_bad_packed_object(struct packed_git *p, const unsigned char *sha1)
+{
+ unsigned i;
+ for (i = 0; i < p->num_bad_objects; i++)
+ if (!hashcmp(sha1, p->bad_object_sha1 + GIT_SHA1_RAWSZ * i))
+ return;
+ p->bad_object_sha1 = xrealloc(p->bad_object_sha1,
+ st_mult(GIT_MAX_RAWSZ,
+ st_add(p->num_bad_objects, 1)));
+ hashcpy(p->bad_object_sha1 + GIT_SHA1_RAWSZ * p->num_bad_objects, sha1);
+ p->num_bad_objects++;
+}
+
+const struct packed_git *has_packed_and_bad(const unsigned char *sha1)
+{
+ struct packed_git *p;
+ unsigned i;
+
+ for (p = packed_git; p; p = p->next)
+ for (i = 0; i < p->num_bad_objects; i++)
+ if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
+ return p;
+ return NULL;
+}
+
+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 = use_pack(p, w_curs, *curpos, NULL);
+ off_t base_offset;
+
+ /* 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;
+ while (c & 128) {
+ base_offset += 1;
+ if (!base_offset || MSB(base_offset, 7))
+ return 0; /* overflow */
+ c = base_info[used++];
+ base_offset = (base_offset << 7) + (c & 127);
+ }
+ base_offset = delta_obj_offset - base_offset;
+ if (base_offset <= 0 || base_offset >= delta_obj_offset)
+ return 0; /* out of bound */
+ *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);
+ *curpos += 20;
+ } else
+ die("I am totally screwed");
+ return base_offset;
+}
+
+/*
+ * Like get_delta_base above, but we return the sha1 instead of the pack
+ * offset. This means it is cheaper for REF deltas (we do not have to do
+ * the final object lookup), but more expensive for OFS deltas (we
+ * have to load the revidx to convert the offset back into a sha1).
+ */
+static const unsigned char *get_delta_base_sha1(struct packed_git *p,
+ struct pack_window **w_curs,
+ off_t curpos,
+ enum object_type type,
+ off_t delta_obj_offset)
+{
+ if (type == OBJ_REF_DELTA) {
+ unsigned char *base = use_pack(p, w_curs, curpos, NULL);
+ return base;
+ } else if (type == OBJ_OFS_DELTA) {
+ struct revindex_entry *revidx;
+ off_t base_offset = get_delta_base(p, w_curs, &curpos,
+ type, delta_obj_offset);
+
+ if (!base_offset)
+ return NULL;
+
+ revidx = find_pack_revindex(p, base_offset);
+ if (!revidx)
+ return NULL;
+
+ return nth_packed_object_sha1(p, revidx->nr);
+ } else
+ return NULL;
+}
+
+static int retry_bad_packed_offset(struct packed_git *p, off_t obj_offset)
+{
+ int type;
+ struct revindex_entry *revidx;
+ const unsigned char *sha1;
+ revidx = find_pack_revindex(p, obj_offset);
+ if (!revidx)
+ return OBJ_BAD;
+ sha1 = nth_packed_object_sha1(p, revidx->nr);
+ mark_bad_packed_object(p, sha1);
+ type = sha1_object_info(sha1, 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,
+ off_t obj_offset,
+ enum object_type type,
+ struct pack_window **w_curs,
+ off_t curpos)
+{
+ off_t small_poi_stack[POI_STACK_PREALLOC];
+ off_t *poi_stack = small_poi_stack;
+ int poi_stack_nr = 0, poi_stack_alloc = POI_STACK_PREALLOC;
+
+ while (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
+ off_t base_offset;
+ unsigned long size;
+ /* Push the object we're going to leave behind */
+ if (poi_stack_nr >= poi_stack_alloc && poi_stack == small_poi_stack) {
+ poi_stack_alloc = alloc_nr(poi_stack_nr);
+ ALLOC_ARRAY(poi_stack, poi_stack_alloc);
+ memcpy(poi_stack, small_poi_stack, sizeof(off_t)*poi_stack_nr);
+ } else {
+ ALLOC_GROW(poi_stack, poi_stack_nr+1, poi_stack_alloc);
+ }
+ poi_stack[poi_stack_nr++] = obj_offset;
+ /* If parsing the base offset fails, just unwind */
+ base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset);
+ if (!base_offset)
+ goto unwind;
+ curpos = obj_offset = base_offset;
+ type = unpack_object_header(p, w_curs, &curpos, &size);
+ 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);
+ if (type > OBJ_NONE)
+ goto out;
+ goto unwind;
+ }
+ }
+
+ switch (type) {
+ case OBJ_BAD:
+ case OBJ_COMMIT:
+ case OBJ_TREE:
+ case OBJ_BLOB:
+ case OBJ_TAG:
+ break;
+ default:
+ error("unknown object type %i at offset %"PRIuMAX" in %s",
+ type, (uintmax_t)obj_offset, p->pack_name);
+ type = OBJ_BAD;
+ }
+
+out:
+ if (poi_stack != small_poi_stack)
+ free(poi_stack);
+ return type;
+
+unwind:
+ while (poi_stack_nr) {
+ obj_offset = poi_stack[--poi_stack_nr];
+ type = retry_bad_packed_offset(p, obj_offset);
+ if (type > OBJ_NONE)
+ goto out;
+ }
+ type = OBJ_BAD;
+ goto out;
+}
+
+static struct hashmap delta_base_cache;
+static size_t delta_base_cached;
+
+static LIST_HEAD(delta_base_cache_lru);
+
+struct delta_base_cache_key {
+ struct packed_git *p;
+ off_t base_offset;
+};
+
+struct delta_base_cache_entry {
+ struct hashmap hash;
+ struct delta_base_cache_key key;
+ struct list_head lru;
+ void *data;
+ unsigned long size;
+ enum object_type type;
+};
+
+static unsigned int pack_entry_hash(struct packed_git *p, off_t base_offset)
+{
+ unsigned int hash;
+
+ hash = (unsigned int)(intptr_t)p + (unsigned int)base_offset;
+ hash += (hash >> 8) + (hash >> 16);
+ return hash;
+}
+
+static struct delta_base_cache_entry *
+get_delta_base_cache_entry(struct packed_git *p, off_t base_offset)
+{
+ struct hashmap_entry entry;
+ struct delta_base_cache_key key;
+
+ if (!delta_base_cache.cmpfn)
+ return NULL;
+
+ hashmap_entry_init(&entry, pack_entry_hash(p, base_offset));
+ key.p = p;
+ key.base_offset = base_offset;
+ return hashmap_get(&delta_base_cache, &entry, &key);
+}
+
+static int delta_base_cache_key_eq(const struct delta_base_cache_key *a,
+ const struct delta_base_cache_key *b)
+{
+ return a->p == b->p && a->base_offset == b->base_offset;
+}
+
+static int delta_base_cache_hash_cmp(const void *unused_cmp_data,
+ const void *va, const void *vb,
+ const void *vkey)
+{
+ const struct delta_base_cache_entry *a = va, *b = vb;
+ const struct delta_base_cache_key *key = vkey;
+ if (key)
+ return !delta_base_cache_key_eq(&a->key, key);
+ else
+ return !delta_base_cache_key_eq(&a->key, &b->key);
+}
+
+static int in_delta_base_cache(struct packed_git *p, off_t base_offset)
+{
+ return !!get_delta_base_cache_entry(p, base_offset);
+}
+
+/*
+ * Remove the entry from the cache, but do _not_ free the associated
+ * entry data. The caller takes ownership of the "data" buffer, and
+ * should copy out any fields it wants before detaching.
+ */
+static void detach_delta_base_cache_entry(struct delta_base_cache_entry *ent)
+{
+ hashmap_remove(&delta_base_cache, ent, &ent->key);
+ list_del(&ent->lru);
+ delta_base_cached -= ent->size;
+ free(ent);
+}
+
+static void *cache_or_unpack_entry(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);
+
+ if (type)
+ *type = ent->type;
+ if (base_size)
+ *base_size = ent->size;
+ return xmemdupz(ent->data, ent->size);
+}
+
+static inline void release_delta_base_cache(struct delta_base_cache_entry *ent)
+{
+ free(ent->data);
+ detach_delta_base_cache_entry(ent);
+}
+
+void clear_delta_base_cache(void)
+{
+ struct list_head *lru, *tmp;
+ list_for_each_safe(lru, tmp, &delta_base_cache_lru) {
+ struct delta_base_cache_entry *entry =
+ list_entry(lru, struct delta_base_cache_entry, lru);
+ release_delta_base_cache(entry);
+ }
+}
+
+static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
+ void *base, unsigned long base_size, enum object_type type)
+{
+ struct delta_base_cache_entry *ent = xmalloc(sizeof(*ent));
+ struct list_head *lru, *tmp;
+
+ delta_base_cached += base_size;
+
+ list_for_each_safe(lru, tmp, &delta_base_cache_lru) {
+ struct delta_base_cache_entry *f =
+ list_entry(lru, struct delta_base_cache_entry, lru);
+ if (delta_base_cached <= delta_base_cache_limit)
+ break;
+ release_delta_base_cache(f);
+ }
+
+ ent->key.p = p;
+ ent->key.base_offset = base_offset;
+ ent->type = type;
+ ent->data = base;
+ ent->size = base_size;
+ list_add_tail(&ent->lru, &delta_base_cache_lru);
+
+ if (!delta_base_cache.cmpfn)
+ hashmap_init(&delta_base_cache, delta_base_cache_hash_cmp, NULL, 0);
+ hashmap_entry_init(ent, pack_entry_hash(p, base_offset));
+ hashmap_add(&delta_base_cache, ent);
+}
+
+int packed_object_info(struct packed_git *p, off_t obj_offset,
+ struct object_info *oi)
+{
+ struct pack_window *w_curs = NULL;
+ unsigned long size;
+ off_t curpos = obj_offset;
+ enum object_type type;
+
+ /*
+ * We always get the representation type, but only convert it to
+ * a "real" type later if the caller is interested.
+ */
+ if (oi->contentp) {
+ *oi->contentp = cache_or_unpack_entry(p, obj_offset, oi->sizep,
+ &type);
+ if (!*oi->contentp)
+ type = OBJ_BAD;
+ } else {
+ type = unpack_object_header(p, &w_curs, &curpos, &size);
+ }
+
+ if (!oi->contentp && oi->sizep) {
+ if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
+ off_t tmp_pos = curpos;
+ off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos,
+ type, obj_offset);
+ if (!base_offset) {
+ type = OBJ_BAD;
+ goto out;
+ }
+ *oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos);
+ if (*oi->sizep == 0) {
+ type = OBJ_BAD;
+ goto out;
+ }
+ } else {
+ *oi->sizep = size;
+ }
+ }
+
+ if (oi->disk_sizep) {
+ struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
+ *oi->disk_sizep = revidx[1].offset - obj_offset;
+ }
+
+ if (oi->typep || oi->typename) {
+ enum object_type ptot;
+ ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
+ curpos);
+ if (oi->typep)
+ *oi->typep = ptot;
+ if (oi->typename) {
+ const char *tn = typename(ptot);
+ if (tn)
+ strbuf_addstr(oi->typename, tn);
+ }
+ if (ptot < 0) {
+ type = OBJ_BAD;
+ goto out;
+ }
+ }
+
+ if (oi->delta_base_sha1) {
+ if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
+ const unsigned char *base;
+
+ base = get_delta_base_sha1(p, &w_curs, curpos,
+ type, obj_offset);
+ if (!base) {
+ type = OBJ_BAD;
+ goto out;
+ }
+
+ hashcpy(oi->delta_base_sha1, base);
+ } else
+ hashclr(oi->delta_base_sha1);
+ }
+
+ oi->whence = in_delta_base_cache(p, obj_offset) ? OI_DBCACHED :
+ OI_PACKED;
+
+out:
+ unuse_pack(&w_curs);
+ return type;
+}
+
+static void *unpack_compressed_entry(struct packed_git *p,
+ struct pack_window **w_curs,
+ off_t curpos,
+ unsigned long size)
+{
+ int st;
+ git_zstream stream;
+ unsigned char *buffer, *in;
+
+ buffer = xmallocz_gently(size);
+ if (!buffer)
+ return NULL;
+ memset(&stream, 0, sizeof(stream));
+ stream.next_out = buffer;
+ stream.avail_out = size + 1;
+
+ git_inflate_init(&stream);
+ do {
+ in = use_pack(p, w_curs, curpos, &stream.avail_in);
+ stream.next_in = in;
+ st = git_inflate(&stream, Z_FINISH);
+ if (!stream.avail_out)
+ break; /* the payload is larger than it should be */
+ curpos += stream.next_in - in;
+ } while (st == Z_OK || st == Z_BUF_ERROR);
+ git_inflate_end(&stream);
+ if ((st != Z_STREAM_END) || stream.total_out != size) {
+ free(buffer);
+ return NULL;
+ }
+
+ return buffer;
+}
+
+static void write_pack_access_log(struct packed_git *p, off_t obj_offset)
+{
+ static struct trace_key pack_access = TRACE_KEY_INIT(PACK_ACCESS);
+ trace_printf_key(&pack_access, "%s %"PRIuMAX"\n",
+ p->pack_name, (uintmax_t)obj_offset);
+}
+
+int do_check_packed_object_crc;
+
+#define UNPACK_ENTRY_STACK_PREALLOC 64
+struct unpack_entry_stack_ent {
+ off_t obj_offset;
+ off_t curpos;
+ unsigned long size;
+};
+
+static void *read_object(const unsigned char *sha1, enum object_type *type,
+ unsigned long *size)
+{
+ struct object_info oi = OBJECT_INFO_INIT;
+ void *content;
+ oi.typep = type;
+ oi.sizep = size;
+ oi.contentp = &content;
+
+ if (sha1_object_info_extended(sha1, &oi, 0) < 0)
+ return NULL;
+ return content;
+}
+
+void *unpack_entry(struct packed_git *p, off_t obj_offset,
+ enum object_type *final_type, unsigned long *final_size)
+{
+ struct pack_window *w_curs = NULL;
+ off_t curpos = obj_offset;
+ void *data = NULL;
+ unsigned long size;
+ enum object_type type;
+ struct unpack_entry_stack_ent small_delta_stack[UNPACK_ENTRY_STACK_PREALLOC];
+ struct unpack_entry_stack_ent *delta_stack = small_delta_stack;
+ int delta_stack_nr = 0, delta_stack_alloc = UNPACK_ENTRY_STACK_PREALLOC;
+ int base_from_cache = 0;
+
+ write_pack_access_log(p, obj_offset);
+
+ /* PHASE 1: drill down to the innermost base object */
+ for (;;) {
+ off_t base_offset;
+ int i;
+ struct delta_base_cache_entry *ent;
+
+ ent = get_delta_base_cache_entry(p, curpos);
+ if (ent) {
+ type = ent->type;
+ data = ent->data;
+ size = ent->size;
+ detach_delta_base_cache_entry(ent);
+ base_from_cache = 1;
+ break;
+ }
+
+ if (do_check_packed_object_crc && p->index_version > 1) {
+ struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
+ off_t len = revidx[1].offset - obj_offset;
+ if (check_pack_crc(p, &w_curs, obj_offset, len, revidx->nr)) {
+ const unsigned char *sha1 =
+ nth_packed_object_sha1(p, revidx->nr);
+ error("bad packed object CRC for %s",
+ sha1_to_hex(sha1));
+ mark_bad_packed_object(p, sha1);
+ data = NULL;
+ goto out;
+ }
+ }
+
+ type = unpack_object_header(p, &w_curs, &curpos, &size);
+ if (type != OBJ_OFS_DELTA && type != OBJ_REF_DELTA)
+ break;
+
+ base_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset);
+ if (!base_offset) {
+ error("failed to validate delta base reference "
+ "at offset %"PRIuMAX" from %s",
+ (uintmax_t)curpos, p->pack_name);
+ /* bail to phase 2, in hopes of recovery */
+ data = NULL;
+ break;
+ }
+
+ /* push object, proceed to base */
+ if (delta_stack_nr >= delta_stack_alloc
+ && delta_stack == small_delta_stack) {
+ delta_stack_alloc = alloc_nr(delta_stack_nr);
+ ALLOC_ARRAY(delta_stack, delta_stack_alloc);
+ memcpy(delta_stack, small_delta_stack,
+ sizeof(*delta_stack)*delta_stack_nr);
+ } else {
+ ALLOC_GROW(delta_stack, delta_stack_nr+1, delta_stack_alloc);
+ }
+ i = delta_stack_nr++;
+ delta_stack[i].obj_offset = obj_offset;
+ delta_stack[i].curpos = curpos;
+ delta_stack[i].size = size;
+
+ curpos = obj_offset = base_offset;
+ }
+
+ /* PHASE 2: handle the base */
+ switch (type) {
+ case OBJ_OFS_DELTA:
+ case OBJ_REF_DELTA:
+ if (data)
+ die("BUG: unpack_entry: left loop at a valid delta");
+ break;
+ case OBJ_COMMIT:
+ case OBJ_TREE:
+ case OBJ_BLOB:
+ case OBJ_TAG:
+ if (!base_from_cache)
+ data = unpack_compressed_entry(p, &w_curs, curpos, size);
+ break;
+ default:
+ data = NULL;
+ error("unknown object type %i at offset %"PRIuMAX" in %s",
+ type, (uintmax_t)obj_offset, p->pack_name);
+ }
+
+ /* PHASE 3: apply deltas in order */
+
+ /* invariants:
+ * 'data' holds the base data, or NULL if there was corruption
+ */
+ while (delta_stack_nr) {
+ void *delta_data;
+ void *base = data;
+ void *external_base = NULL;
+ unsigned long delta_size, base_size = size;
+ int i;
+
+ data = NULL;
+
+ if (base)
+ add_delta_base_cache(p, obj_offset, base, base_size, type);
+
+ if (!base) {
+ /*
+ * We're probably in deep shit, but let's try to fetch
+ * the required base anyway from another pack or loose.
+ * This is costly but should happen only in the presence
+ * of a corrupted pack, and is better than failing outright.
+ */
+ struct revindex_entry *revidx;
+ const unsigned char *base_sha1;
+ revidx = find_pack_revindex(p, obj_offset);
+ if (revidx) {
+ base_sha1 = nth_packed_object_sha1(p, revidx->nr);
+ error("failed to read delta base object %s"
+ " at offset %"PRIuMAX" from %s",
+ sha1_to_hex(base_sha1), (uintmax_t)obj_offset,
+ p->pack_name);
+ mark_bad_packed_object(p, base_sha1);
+ base = read_object(base_sha1, &type, &base_size);
+ external_base = base;
+ }
+ }
+
+ i = --delta_stack_nr;
+ obj_offset = delta_stack[i].obj_offset;
+ curpos = delta_stack[i].curpos;
+ delta_size = delta_stack[i].size;
+
+ if (!base)
+ continue;
+
+ delta_data = unpack_compressed_entry(p, &w_curs, curpos, delta_size);
+
+ if (!delta_data) {
+ error("failed to unpack compressed delta "
+ "at offset %"PRIuMAX" from %s",
+ (uintmax_t)curpos, p->pack_name);
+ data = NULL;
+ free(external_base);
+ continue;
+ }
+
+ data = patch_delta(base, base_size,
+ delta_data, delta_size,
+ &size);
+
+ /*
+ * We could not apply the delta; warn the user, but keep going.
+ * Our failure will be noticed either in the next iteration of
+ * the loop, or if this is the final delta, in the caller when
+ * we return NULL. Those code paths will take care of making
+ * a more explicit warning and retrying with another copy of
+ * the object.
+ */
+ if (!data)
+ error("failed to apply delta");
+
+ free(delta_data);
+ free(external_base);
+ }
+
+ if (final_type)
+ *final_type = type;
+ if (final_size)
+ *final_size = size;
+
+out:
+ unuse_pack(&w_curs);
+
+ if (delta_stack != small_delta_stack)
+ free(delta_stack);
+
+ return data;
+}
+
+const unsigned char *nth_packed_object_sha1(struct packed_git *p,
+ uint32_t n)
+{
+ 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;
+ }
+}
+
+const struct object_id *nth_packed_object_oid(struct object_id *oid,
+ struct packed_git *p,
+ uint32_t n)
+{
+ const unsigned char *hash = nth_packed_object_sha1(p, n);
+ if (!hash)
+ return NULL;
+ hashcpy(oid->hash, hash);
+ return oid;
+}
+
+void check_pack_index_ptr(const struct packed_git *p, const void *vptr)
+{
+ const unsigned char *ptr = vptr;
+ const unsigned char *start = p->index_data;
+ const unsigned char *end = start + p->index_size;
+ if (ptr < start)
+ die(_("offset before start of pack index for %s (corrupt index?)"),
+ p->pack_name);
+ /* No need to check for underflow; .idx files must be at least 8 bytes */
+ if (ptr >= end - 8)
+ die(_("offset beyond end of pack index for %s (truncated index?)"),
+ p->pack_name);
+}
+
+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 (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;
+ check_pack_index_ptr(p, index);
+ 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;
+ const unsigned char *index = p->index_data;
+ unsigned hi, lo, stride;
+ static int debug_lookup = -1;
+
+ if (debug_lookup < 0)
+ debug_lookup = !!getenv("GIT_DEBUG_LOOKUP");
+
+ 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]));
+ if (p->index_version > 1) {
+ stride = 20;
+ } else {
+ stride = 24;
+ index += 4;
+ }
+
+ if (debug_lookup)
+ printf("%02x%02x%02x... lo %u hi %u nr %"PRIu32"\n",
+ sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects);
+
+ while (lo < hi) {
+ unsigned mi = (lo + hi) / 2;
+ int cmp = hashcmp(index + mi * stride, sha1);
+
+ if (debug_lookup)
+ printf("lo %u hi %u rg %u mi %u\n",
+ lo, hi, hi - lo, mi);
+ if (!cmp)
+ return nth_packed_object_offset(p, mi);
+ if (cmp > 0)
+ hi = mi;
+ else
+ lo = mi+1;
+ }
+ return 0;
+}
+
+int is_pack_valid(struct packed_git *p)
+{
+ /* An already open pack is known to be valid. */
+ if (p->pack_fd != -1)
+ return 1;
+
+ /* If the pack has one window completely covering the
+ * file size, the pack is known to be valid even if
+ * the descriptor is not currently open.
+ */
+ if (p->windows) {
+ struct pack_window *w = p->windows;
+
+ if (!w->offset && w->len == p->pack_size)
+ return 1;
+ }
+
+ /* Force the pack to open to prove its valid. */
+ return !open_packed_git(p);
+}
+
+struct packed_git *find_sha1_pack(const unsigned char *sha1,
+ struct packed_git *packs)
+{
+ struct packed_git *p;
+
+ for (p = packs; p; p = p->next) {
+ if (find_pack_entry_one(sha1, p))
+ return p;
+ }
+ return NULL;
+
+}
+
+static int fill_pack_entry(const unsigned char *sha1,
+ struct pack_entry *e,
+ struct packed_git *p)
+{
+ off_t offset;
+
+ if (p->num_bad_objects) {
+ unsigned i;
+ for (i = 0; i < p->num_bad_objects; i++)
+ if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
+ return 0;
+ }
+
+ offset = find_pack_entry_one(sha1, p);
+ if (!offset)
+ return 0;
+
+ /*
+ * We are about to tell the caller where they can locate the
+ * requested object. We better make sure the packfile is
+ * still here and can be accessed before supplying that
+ * answer, as it may have been deleted since the index was
+ * loaded!
+ */
+ if (!is_pack_valid(p))
+ return 0;
+ e->offset = offset;
+ e->p = p;
+ hashcpy(e->sha1, sha1);
+ return 1;
+}
+
+/*
+ * Iff a pack file contains the object named by sha1, return true and
+ * store its location to e.
+ */
+int find_pack_entry(const unsigned char *sha1, struct pack_entry *e)
+{
+ struct mru_entry *p;
+
+ prepare_packed_git();
+ if (!packed_git)
+ return 0;
+
+ for (p = packed_git_mru->head; p; p = p->next) {
+ if (fill_pack_entry(sha1, e, p->item)) {
+ mru_mark(packed_git_mru, p);
+ return 1;
+ }
+ }
+ return 0;
+}
+
+int has_sha1_pack(const unsigned char *sha1)
+{
+ struct pack_entry e;
+ return find_pack_entry(sha1, &e);
+}
+
+int has_pack_index(const unsigned char *sha1)
+{
+ struct stat st;
+ if (stat(sha1_pack_index_name(sha1), &st))
+ return 0;
+ return 1;
+}
+
+static int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn cb, void *data)
+{
+ uint32_t i;
+ int r = 0;
+
+ for (i = 0; i < p->num_objects; i++) {
+ struct object_id oid;
+
+ if (!nth_packed_object_oid(&oid, p, i))
+ return error("unable to get sha1 of object %u in %s",
+ i, p->pack_name);
+
+ r = cb(&oid, p, i, data);
+ if (r)
+ break;
+ }
+ return r;
+}
+
+int for_each_packed_object(each_packed_object_fn cb, void *data, unsigned flags)
+{
+ struct packed_git *p;
+ int r = 0;
+ int pack_errors = 0;
+
+ prepare_packed_git();
+ for (p = packed_git; p; p = p->next) {
+ if ((flags & FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local)
+ continue;
+ if (open_pack_index(p)) {
+ pack_errors = 1;
+ continue;
+ }
+ r = for_each_object_in_pack(p, cb, data);
+ if (r)
+ break;
+ }
+ return r ? r : pack_errors;
+}