diff options
Diffstat (limited to 'builtin-pack-objects.c')
| -rw-r--r-- | builtin-pack-objects.c | 419 |
1 files changed, 307 insertions, 112 deletions
diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c index 2f99212..96c069a 100644 --- a/builtin-pack-objects.c +++ b/builtin-pack-objects.c @@ -9,10 +9,13 @@ #include "pack.h" #include "csum-file.h" #include "tree-walk.h" +#include "diff.h" +#include "revision.h" +#include "list-objects.h" #include <sys/time.h> #include <signal.h> -static const char pack_usage[] = "git-pack-objects [-q] [--no-reuse-delta] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list"; +static const char pack_usage[] = "git-pack-objects [-q] [--no-reuse-delta] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] [--revs [--unpacked | --all]*] [--stdout | base-name] <ref-list | <object-list]"; struct object_entry { unsigned char sha1[20]; @@ -53,18 +56,20 @@ struct object_entry { */ static unsigned char object_list_sha1[20]; -static int non_empty = 0; -static int no_reuse_delta = 0; -static int local = 0; -static int incremental = 0; +static int non_empty; +static int no_reuse_delta; +static int local; +static int incremental; static struct object_entry **sorted_by_sha, **sorted_by_type; -static struct object_entry *objects = NULL; -static int nr_objects = 0, nr_alloc = 0, nr_result = 0; +static struct object_entry *objects; +static int nr_objects, nr_alloc, nr_result; static const char *base_name; static unsigned char pack_file_sha1[20]; static int progress = 1; -static volatile sig_atomic_t progress_update = 0; +static volatile sig_atomic_t progress_update; static int window = 10; +static int pack_to_stdout; +static int num_preferred_base; /* * The object names in objects array are hashed with this hashtable, @@ -72,8 +77,8 @@ static int window = 10; * sorted_by_sha is also possible but this was easier to code and faster. * This hashtable is built after all the objects are seen. */ -static int *object_ix = NULL; -static int object_ix_hashsz = 0; +static int *object_ix; +static int object_ix_hashsz; /* * Pack index for existing packs give us easy access to the offsets into @@ -90,15 +95,15 @@ struct pack_revindex { struct packed_git *p; unsigned long *revindex; } *pack_revindex = NULL; -static int pack_revindex_hashsz = 0; +static int pack_revindex_hashsz; /* * stats */ -static int written = 0; -static int written_delta = 0; -static int reused = 0; -static int reused_delta = 0; +static int written; +static int written_delta; +static int reused; +static int reused_delta; static int pack_revindex_ix(struct packed_git *p) { @@ -242,6 +247,82 @@ static int encode_header(enum object_type type, unsigned long size, unsigned cha return n; } +static int check_inflate(unsigned char *data, unsigned long len, unsigned long expect) +{ + z_stream stream; + unsigned char fakebuf[4096]; + int st; + + memset(&stream, 0, sizeof(stream)); + stream.next_in = data; + stream.avail_in = len; + stream.next_out = fakebuf; + stream.avail_out = sizeof(fakebuf); + inflateInit(&stream); + + while (1) { + st = inflate(&stream, Z_FINISH); + if (st == Z_STREAM_END || st == Z_OK) { + st = (stream.total_out == expect && + stream.total_in == len) ? 0 : -1; + break; + } + if (st != Z_BUF_ERROR) { + st = -1; + break; + } + stream.next_out = fakebuf; + stream.avail_out = sizeof(fakebuf); + } + inflateEnd(&stream); + return st; +} + +/* + * we are going to reuse the existing pack entry data. make + * sure it is not corrupt. + */ +static int revalidate_pack_entry(struct object_entry *entry, unsigned char *data, unsigned long len) +{ + enum object_type type; + unsigned long size, used; + + if (pack_to_stdout) + return 0; + + /* the caller has already called use_packed_git() for us, + * so it is safe to access the pack data from mmapped location. + * make sure the entry inflates correctly. + */ + used = unpack_object_header_gently(data, len, &type, &size); + if (!used) + return -1; + if (type == OBJ_DELTA) + used += 20; /* skip base object name */ + data += used; + len -= used; + return check_inflate(data, len, entry->size); +} + +static int revalidate_loose_object(struct object_entry *entry, + unsigned char *map, + unsigned long mapsize) +{ + /* we already know this is a loose object with new type header. */ + enum object_type type; + unsigned long size, used; + + if (pack_to_stdout) + return 0; + + used = unpack_object_header_gently(map, mapsize, &type, &size); + if (!used) + return -1; + map += used; + mapsize -= used; + return check_inflate(map, mapsize, size); +} + static unsigned long write_object(struct sha1file *f, struct object_entry *entry) { @@ -276,6 +357,9 @@ static unsigned long write_object(struct sha1file *f, map = map_sha1_file(entry->sha1, &mapsize); if (map && !legacy_loose_object(map)) { /* We can copy straight into the pack file */ + if (revalidate_loose_object(entry, map, mapsize)) + die("corrupt loose object %s", + sha1_to_hex(entry->sha1)); sha1write(f, map, mapsize); munmap(map, mapsize); written++; @@ -286,7 +370,7 @@ static unsigned long write_object(struct sha1file *f, munmap(map, mapsize); } - if (! to_reuse) { + if (!to_reuse) { buf = read_sha1_file(entry->sha1, type, &size); if (!buf) die("unable to read %s", sha1_to_hex(entry->sha1)); @@ -319,6 +403,9 @@ static unsigned long write_object(struct sha1file *f, datalen = find_packed_object_size(p, entry->in_pack_offset); buf = (char *) p->pack_base + entry->in_pack_offset; + + if (revalidate_pack_entry(entry, buf, datalen)) + die("corrupt delta in pack %s", sha1_to_hex(entry->sha1)); sha1write(f, buf, datalen); unuse_packed_git(p); hdrlen = 0; /* not really */ @@ -441,7 +528,7 @@ static int locate_object_entry_hash(const unsigned char *sha1) memcpy(&ui, sha1, sizeof(unsigned int)); i = ui % object_ix_hashsz; while (0 < object_ix[i]) { - if (!memcmp(sha1, objects[object_ix[i]-1].sha1, 20)) + if (!hashcmp(sha1, objects[object_ix[i] - 1].sha1)) return i; if (++i == object_ix_hashsz) i = 0; @@ -510,15 +597,15 @@ static int add_object_entry(const unsigned char *sha1, unsigned hash, int exclud if (!exclude) { for (p = packed_git; p; p = p->next) { - struct pack_entry e; - if (find_pack_entry_one(sha1, &e, p)) { + unsigned long offset = find_pack_entry_one(sha1, p); + if (offset) { if (incremental) return 0; if (local && !p->pack_local) return 0; if (!found_pack) { - found_offset = e.offset; - found_pack = e.p; + found_offset = offset; + found_pack = p; } } } @@ -534,7 +621,7 @@ static int add_object_entry(const unsigned char *sha1, unsigned hash, int exclud entry = objects + idx; nr_objects = idx + 1; memset(entry, 0, sizeof(*entry)); - memcpy(entry->sha1, sha1, 20); + hashcpy(entry->sha1, sha1); entry->hash = hash; if (object_ix_hashsz * 3 <= nr_objects * 4) @@ -607,7 +694,7 @@ static struct pbase_tree_cache *pbase_tree_get(const unsigned char *sha1) */ for (neigh = 0; neigh < 8; neigh++) { ent = pbase_tree_cache[my_ix]; - if (ent && !memcmp(ent->sha1, sha1, 20)) { + if (ent && !hashcmp(ent->sha1, sha1)) { ent->ref++; return ent; } @@ -649,7 +736,7 @@ static struct pbase_tree_cache *pbase_tree_get(const unsigned char *sha1) free(ent->tree_data); nent = ent; } - memcpy(nent->sha1, sha1, 20); + hashcpy(nent->sha1, sha1); nent->tree_data = data; nent->tree_size = size; nent->ref = 1; @@ -755,7 +842,7 @@ static int check_pbase_path(unsigned hash) return 0; } -static void add_preferred_base_object(char *name, unsigned hash) +static void add_preferred_base_object(const char *name, unsigned hash) { struct pbase_tree *it; int cmplen = name_cmp_len(name); @@ -784,12 +871,15 @@ static void add_preferred_base(unsigned char *sha1) unsigned long size; unsigned char tree_sha1[20]; + if (window <= num_preferred_base++) + return; + data = read_object_with_reference(sha1, tree_type, &size, tree_sha1); if (!data) return; for (it = pbase_tree; it; it = it->next) { - if (!memcmp(it->pcache.sha1, tree_sha1, 20)) { + if (!hashcmp(it->pcache.sha1, tree_sha1)) { free(data); return; } @@ -799,7 +889,7 @@ static void add_preferred_base(unsigned char *sha1) it->next = pbase_tree; pbase_tree = it; - memcpy(it->pcache.sha1, tree_sha1, 20); + hashcpy(it->pcache.sha1, tree_sha1); it->pcache.tree_data = data; it->pcache.tree_size = size; } @@ -931,7 +1021,7 @@ static struct object_entry **create_sorted_list(entry_sort_t sort) static int sha1_sort(const struct object_entry *a, const struct object_entry *b) { - return memcmp(a->sha1, b->sha1, 20); + return hashcmp(a->sha1, b->sha1); } static struct object_entry **create_final_object_list(void) @@ -1163,7 +1253,7 @@ static void prepare_pack(int window, int depth) find_deltas(sorted_by_type, window+1, depth); } -static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout) +static int reuse_cached_pack(unsigned char *sha1) { static const char cache[] = "pack-cache/pack-%s.%s"; char *cached_pack, *cached_idx; @@ -1243,14 +1333,105 @@ static int git_pack_config(const char *k, const char *v) return git_default_config(k, v); } +static void read_object_list_from_stdin(void) +{ + char line[40 + 1 + PATH_MAX + 2]; + unsigned char sha1[20]; + unsigned hash; + + for (;;) { + if (!fgets(line, sizeof(line), stdin)) { + if (feof(stdin)) + break; + if (!ferror(stdin)) + die("fgets returned NULL, not EOF, not error!"); + if (errno != EINTR) + die("fgets: %s", strerror(errno)); + clearerr(stdin); + continue; + } + if (line[0] == '-') { + if (get_sha1_hex(line+1, sha1)) + die("expected edge sha1, got garbage:\n %s", + line); + add_preferred_base(sha1); + continue; + } + if (get_sha1_hex(line, sha1)) + die("expected sha1, got garbage:\n %s", line); + + hash = name_hash(line+41); + add_preferred_base_object(line+41, hash); + add_object_entry(sha1, hash, 0); + } +} + +static void show_commit(struct commit *commit) +{ + unsigned hash = name_hash(""); + add_preferred_base_object("", hash); + add_object_entry(commit->object.sha1, hash, 0); +} + +static void show_object(struct object_array_entry *p) +{ + unsigned hash = name_hash(p->name); + add_preferred_base_object(p->name, hash); + add_object_entry(p->item->sha1, hash, 0); +} + +static void show_edge(struct commit *commit) +{ + add_preferred_base(commit->object.sha1); +} + +static void get_object_list(int ac, const char **av) +{ + struct rev_info revs; + char line[1000]; + int flags = 0; + + init_revisions(&revs, NULL); + save_commit_buffer = 0; + track_object_refs = 0; + setup_revisions(ac, av, &revs, NULL); + + while (fgets(line, sizeof(line), stdin) != NULL) { + int len = strlen(line); + if (line[len - 1] == '\n') + line[--len] = 0; + if (!len) + break; + if (*line == '-') { + if (!strcmp(line, "--not")) { + flags ^= UNINTERESTING; + continue; + } + die("not a rev '%s'", line); + } + if (handle_revision_arg(line, &revs, flags, 1)) + die("bad revision '%s'", line); + } + + prepare_revision_walk(&revs); + mark_edges_uninteresting(revs.commits, &revs, show_edge); + traverse_commit_list(&revs, show_commit, show_object); +} + int cmd_pack_objects(int argc, const char **argv, const char *prefix) { SHA_CTX ctx; - char line[40 + 1 + PATH_MAX + 2]; - int depth = 10, pack_to_stdout = 0; + int depth = 10; struct object_entry **list; - int num_preferred_base = 0; + int use_internal_rev_list = 0; + int thin = 0; int i; + const char *rp_av[64]; + int rp_ac; + + rp_av[0] = "pack-objects"; + rp_av[1] = "--objects"; /* --thin will make it --objects-edge */ + rp_ac = 2; git_config(git_pack_config); @@ -1258,63 +1439,99 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) for (i = 1; i < argc; i++) { const char *arg = argv[i]; - if (*arg == '-') { - if (!strcmp("--non-empty", arg)) { - non_empty = 1; - continue; - } - if (!strcmp("--local", arg)) { - local = 1; - continue; - } - if (!strcmp("--progress", arg)) { - progress = 1; - continue; - } - if (!strcmp("--incremental", arg)) { - incremental = 1; - continue; - } - if (!strncmp("--window=", arg, 9)) { - char *end; - window = strtoul(arg+9, &end, 0); - if (!arg[9] || *end) - usage(pack_usage); - continue; - } - if (!strncmp("--depth=", arg, 8)) { - char *end; - depth = strtoul(arg+8, &end, 0); - if (!arg[8] || *end) - usage(pack_usage); - continue; - } - if (!strcmp("--progress", arg)) { - progress = 1; - continue; - } - if (!strcmp("-q", arg)) { - progress = 0; - continue; - } - if (!strcmp("--no-reuse-delta", arg)) { - no_reuse_delta = 1; - continue; - } - if (!strcmp("--stdout", arg)) { - pack_to_stdout = 1; - continue; - } - usage(pack_usage); + if (*arg != '-') + break; + + if (!strcmp("--non-empty", arg)) { + non_empty = 1; + continue; + } + if (!strcmp("--local", arg)) { + local = 1; + continue; + } + if (!strcmp("--progress", arg)) { + progress = 1; + continue; + } + if (!strcmp("--incremental", arg)) { + incremental = 1; + continue; + } + if (!strncmp("--window=", arg, 9)) { + char *end; + window = strtoul(arg+9, &end, 0); + if (!arg[9] || *end) + usage(pack_usage); + continue; + } + if (!strncmp("--depth=", arg, 8)) { + char *end; + depth = strtoul(arg+8, &end, 0); + if (!arg[8] || *end) + usage(pack_usage); + continue; + } + if (!strcmp("--progress", arg)) { + progress = 1; + continue; + } + if (!strcmp("-q", arg)) { + progress = 0; + continue; + } + if (!strcmp("--no-reuse-delta", arg)) { + no_reuse_delta = 1; + continue; + } + if (!strcmp("--stdout", arg)) { + pack_to_stdout = 1; + continue; + } + if (!strcmp("--revs", arg)) { + use_internal_rev_list = 1; + continue; } - if (base_name) - usage(pack_usage); - base_name = arg; + if (!strcmp("--unpacked", arg) || + !strncmp("--unpacked=", arg, 11) || + !strcmp("--all", arg)) { + use_internal_rev_list = 1; + if (ARRAY_SIZE(rp_av) - 1 <= rp_ac) + die("too many internal rev-list options"); + rp_av[rp_ac++] = arg; + continue; + } + if (!strcmp("--thin", arg)) { + use_internal_rev_list = 1; + thin = 1; + rp_av[1] = "--objects-edge"; + continue; + } + usage(pack_usage); } + /* Traditionally "pack-objects [options] base extra" failed; + * we would however want to take refs parameter that would + * have been given to upstream rev-list ourselves, which means + * we somehow want to say what the base name is. So the + * syntax would be: + * + * pack-objects [options] base <refs...> + * + * in other words, we would treat the first non-option as the + * base_name and send everything else to the internal revision + * walker. + */ + + if (!pack_to_stdout) + base_name = argv[i++]; + if (pack_to_stdout != !base_name) usage(pack_usage); + if (!pack_to_stdout && thin) + die("--thin cannot be used to build an indexable pack."); + prepare_packed_git(); if (progress) { @@ -1322,35 +1539,13 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) setup_progress_signal(); } - for (;;) { - unsigned char sha1[20]; - unsigned hash; - - if (!fgets(line, sizeof(line), stdin)) { - if (feof(stdin)) - break; - if (!ferror(stdin)) - die("fgets returned NULL, not EOF, not error!"); - if (errno != EINTR) - die("fgets: %s", strerror(errno)); - clearerr(stdin); - continue; - } - - if (line[0] == '-') { - if (get_sha1_hex(line+1, sha1)) - die("expected edge sha1, got garbage:\n %s", - line+1); - if (num_preferred_base++ < window) - add_preferred_base(sha1); - continue; - } - if (get_sha1_hex(line, sha1)) - die("expected sha1, got garbage:\n %s", line); - hash = name_hash(line+41); - add_preferred_base_object(line+41, hash); - add_object_entry(sha1, hash, 0); + if (!use_internal_rev_list) + read_object_list_from_stdin(); + else { + rp_av[rp_ac] = NULL; + get_object_list(rp_ac, rp_av); } + if (progress) fprintf(stderr, "Done counting %d objects.\n", nr_objects); sorted_by_sha = create_final_object_list(); @@ -1367,7 +1562,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (progress && (nr_objects != nr_result)) fprintf(stderr, "Result has %d objects.\n", nr_result); - if (reuse_cached_pack(object_list_sha1, pack_to_stdout)) + if (reuse_cached_pack(object_list_sha1)) ; else { if (nr_result) |