From: Junio C Hamano Date: Thu, 2 Apr 2009 05:34:19 +0000 (-0700) Subject: Merge branch 'jc/maint-1.6.0-keep-pack' X-Git-Tag: v1.6.3-rc0~52 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/3c91bf6805249d0f59ddff4e5dc4118127527243?ds=inline;hp=-c Merge branch 'jc/maint-1.6.0-keep-pack' * jc/maint-1.6.0-keep-pack: pack-objects: don't loosen objects available in alternate or kept packs t7700: demonstrate repack flaw which may loosen objects unnecessarily Remove --kept-pack-only option and associated infrastructure pack-objects: only repack or loosen objects residing in "local" packs git-repack.sh: don't use --kept-pack-only option to pack-objects t7700-repack: add two new tests demonstrating repacking flaws Conflicts: t/t7700-repack.sh --- 3c91bf6805249d0f59ddff4e5dc4118127527243 diff --combined builtin-pack-objects.c index 2000d97ec4,ad3f8e7751..9fc3b35547 --- a/builtin-pack-objects.c +++ b/builtin-pack-objects.c @@@ -78,7 -78,7 +78,7 @@@ static int progress = 1 static int window = 10; static uint32_t pack_size_limit, pack_size_limit_cfg; static int depth = 50; -static int delta_search_threads = 1; +static int delta_search_threads; static int pack_to_stdout; static int num_preferred_base; static struct progress *progress_state; @@@ -195,16 -195,16 +195,16 @@@ static int check_pack_inflate(struct pa int st; memset(&stream, 0, sizeof(stream)); - inflateInit(&stream); + git_inflate_init(&stream); do { in = use_pack(p, w_curs, offset, &stream.avail_in); stream.next_in = in; stream.next_out = fakebuf; stream.avail_out = sizeof(fakebuf); - st = inflate(&stream, Z_FINISH); + st = git_inflate(&stream, Z_FINISH); offset += stream.next_in - in; } while (st == Z_OK || st == Z_BUF_ERROR); - inflateEnd(&stream); + git_inflate_end(&stream); return (st == Z_STREAM_END && stream.total_out == expect && stream.total_in == len) ? 0 : -1; @@@ -286,7 -286,6 +286,7 @@@ static unsigned long write_object(struc */ if (!to_reuse) { + no_reuse: if (!usable_delta) { buf = read_sha1_file(entry->idx.sha1, &type, &size); if (!buf) @@@ -368,60 -367,46 +368,60 @@@ struct revindex_entry *revidx; off_t offset; - if (entry->delta) { + if (entry->delta) type = (allow_ofs_delta && entry->delta->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; - reused_delta++; - } hdrlen = encode_header(type, entry->size, header); + offset = entry->in_pack_offset; revidx = find_pack_revindex(p, offset); datalen = revidx[1].offset - offset; if (!pack_to_stdout && p->index_version > 1 && - check_pack_crc(p, &w_curs, offset, datalen, revidx->nr)) - die("bad packed object CRC for %s", sha1_to_hex(entry->idx.sha1)); + check_pack_crc(p, &w_curs, offset, datalen, revidx->nr)) { + error("bad packed object CRC for %s", sha1_to_hex(entry->idx.sha1)); + unuse_pack(&w_curs); + goto no_reuse; + } + offset += entry->in_pack_header_size; datalen -= entry->in_pack_header_size; + if (!pack_to_stdout && p->index_version == 1 && + check_pack_inflate(p, &w_curs, offset, datalen, entry->size)) { + error("corrupt packed object for %s", sha1_to_hex(entry->idx.sha1)); + unuse_pack(&w_curs); + goto no_reuse; + } + if (type == OBJ_OFS_DELTA) { off_t ofs = entry->idx.offset - entry->delta->idx.offset; unsigned pos = sizeof(dheader) - 1; dheader[pos] = ofs & 127; while (ofs >>= 7) dheader[--pos] = 128 | (--ofs & 127); - if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) + if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) { + unuse_pack(&w_curs); return 0; + } sha1write(f, header, hdrlen); sha1write(f, dheader + pos, sizeof(dheader) - pos); hdrlen += sizeof(dheader) - pos; + reused_delta++; } else if (type == OBJ_REF_DELTA) { - if (limit && hdrlen + 20 + datalen + 20 >= limit) + if (limit && hdrlen + 20 + datalen + 20 >= limit) { + unuse_pack(&w_curs); return 0; + } sha1write(f, header, hdrlen); sha1write(f, entry->delta->idx.sha1, 20); hdrlen += 20; + reused_delta++; } else { - if (limit && hdrlen + datalen + 20 >= limit) + if (limit && hdrlen + datalen + 20 >= limit) { + unuse_pack(&w_curs); return 0; + } sha1write(f, header, hdrlen); } - - if (!pack_to_stdout && p->index_version == 1 && - check_pack_inflate(p, &w_curs, offset, datalen, entry->size)) - die("corrupt packed object for %s", sha1_to_hex(entry->idx.sha1)); copy_pack_data(f, p, &w_curs, offset, datalen); unuse_pack(&w_curs); reused++; @@@ -488,8 -473,9 +488,8 @@@ static void write_pack_file(void } else { char tmpname[PATH_MAX]; int fd; - snprintf(tmpname, sizeof(tmpname), - "%s/pack/tmp_pack_XXXXXX", get_object_directory()); - fd = xmkstemp(tmpname); + fd = odb_mkstemp(tmpname, sizeof(tmpname), + "pack/tmp_pack_XXXXXX"); pack_tmp_name = xstrdup(tmpname); f = sha1fd(fd, pack_tmp_name); } @@@ -1031,11 -1017,9 +1031,11 @@@ static void check_object(struct object_ * We want in_pack_type even if we do not reuse delta * since non-delta representations could still be reused. */ - used = unpack_object_header_gently(buf, avail, + used = unpack_object_header_buffer(buf, avail, &entry->in_pack_type, &entry->size); + if (used == 0) + goto give_up; /* * Determine if this is a delta and if so whether we can @@@ -1047,8 -1031,6 +1047,8 @@@ /* Not a delta hence we've already got all we need. */ entry->type = entry->in_pack_type; entry->in_pack_header_size = used; + if (entry->type < OBJ_COMMIT || entry->type > OBJ_BLOB) + goto give_up; unuse_pack(&w_curs); return; case OBJ_REF_DELTA: @@@ -1065,25 -1047,19 +1065,25 @@@ ofs = c & 127; while (c & 128) { ofs += 1; - if (!ofs || MSB(ofs, 7)) - die("delta base offset overflow in pack for %s", - sha1_to_hex(entry->idx.sha1)); + if (!ofs || MSB(ofs, 7)) { + error("delta base offset overflow in pack for %s", + sha1_to_hex(entry->idx.sha1)); + goto give_up; + } c = buf[used_0++]; ofs = (ofs << 7) + (c & 127); } - if (ofs >= entry->in_pack_offset) - die("delta base offset out of bound for %s", - sha1_to_hex(entry->idx.sha1)); ofs = entry->in_pack_offset - ofs; + if (ofs <= 0 || ofs >= entry->in_pack_offset) { + error("delta base offset out of bound for %s", + sha1_to_hex(entry->idx.sha1)); + goto give_up; + } if (reuse_delta && !entry->preferred_base) { struct revindex_entry *revidx; revidx = find_pack_revindex(p, ofs); + if (!revidx) + goto give_up; base_ref = nth_packed_object_sha1(p, revidx->nr); } entry->in_pack_header_size = used + used_0; @@@ -1103,7 -1079,6 +1103,7 @@@ */ entry->type = entry->in_pack_type; entry->delta = base_entry; + entry->delta_size = entry->size; entry->delta_sibling = base_entry->delta_child; base_entry->delta_child = entry; unuse_pack(&w_curs); @@@ -1118,8 -1093,6 +1118,8 @@@ */ entry->size = get_size_from_delta(p, &w_curs, entry->in_pack_offset + entry->in_pack_header_size); + if (entry->size == 0) + goto give_up; unuse_pack(&w_curs); return; } @@@ -1129,7 -1102,6 +1129,7 @@@ * with sha1_object_info() to find about the object type * at this point... */ + give_up: unuse_pack(&w_curs); } @@@ -1293,7 -1265,7 +1293,7 @@@ static int try_delta(struct unpacked *t max_size = trg_entry->delta_size; ref_depth = trg->depth; } - max_size = max_size * (max_depth - src->depth) / + max_size = (uint64_t)max_size * (max_depth - src->depth) / (max_depth - ref_depth + 1); if (max_size == 0) return 0; @@@ -1412,10 -1384,12 +1412,10 @@@ static void find_deltas(struct object_e int window, int depth, unsigned *processed) { uint32_t i, idx = 0, count = 0; - unsigned int array_size = window * sizeof(struct unpacked); struct unpacked *array; unsigned long mem_usage = 0; - array = xmalloc(array_size); - memset(array, 0, array_size); + array = xcalloc(window, sizeof(struct unpacked)); for (;;) { struct object_entry *entry; @@@ -1611,18 -1585,11 +1611,18 @@@ static void ll_find_deltas(struct objec find_deltas(list, &list_size, window, depth, processed); return; } + if (progress > pack_to_stdout) + fprintf(stderr, "Delta compression using %d threads.\n", + delta_search_threads); /* Partition the work amongst work threads. */ for (i = 0; i < delta_search_threads; i++) { unsigned sub_size = list_size / (delta_search_threads - i); + /* don't use too small segments or no deltas will be found */ + if (sub_size < 2*window && i+1 < delta_search_threads) + sub_size = 0; + p[i].window = window; p[i].depth = depth; p[i].processed = processed; @@@ -1748,16 -1715,6 +1748,16 @@@ static void prepare_pack(int window, in get_object_details(); + /* + * If we're locally repacking then we need to be doubly careful + * from now on in order to make sure no stealth corruption gets + * propagated to the new pack. Clients receiving streamed packs + * should validate everything they get anyway so no need to incur + * the additional cost here in that case. + */ + if (!pack_to_stdout) + do_check_packed_object_crc = 1; + if (!nr_objects || !window || !depth) return; @@@ -1784,14 -1741,6 +1784,14 @@@ if (entry->type < 0) die("unable to get type of object %s", sha1_to_hex(entry->idx.sha1)); + } else { + if (entry->type < 0) { + /* + * This object is not found, but we + * don't have to include it anyway. + */ + continue; + } } delta_list[n++] = entry; @@@ -1966,7 -1915,7 +1966,7 @@@ static void add_objects_in_unpacked_pac const unsigned char *sha1; struct object *o; - if (p->pack_keep) + if (!p->pack_local || p->pack_keep) continue; if (open_pack_index(p)) die("cannot open pack index"); @@@ -1995,6 -1944,29 +1995,29 @@@ free(in_pack.array); } + static int has_sha1_pack_kept_or_nonlocal(const unsigned char *sha1) + { + static struct packed_git *last_found = (void *)1; + struct packed_git *p; + + p = (last_found != (void *)1) ? last_found : packed_git; + + while (p) { + if ((!p->pack_local || p->pack_keep) && + find_pack_entry_one(sha1, p)) { + last_found = p; + return 1; + } + if (p == last_found) + p = packed_git; + else + p = p->next; + if (p == last_found) + p = p->next; + } + return 0; + } + static void loosen_unused_packed_objects(struct rev_info *revs) { struct packed_git *p; @@@ -2002,7 -1974,7 +2025,7 @@@ const unsigned char *sha1; for (p = packed_git; p; p = p->next) { - if (p->pack_keep) + if (!p->pack_local || p->pack_keep) continue; if (open_pack_index(p)) @@@ -2010,7 -1982,8 +2033,8 @@@ for (i = 0; i < p->num_objects; i++) { sha1 = nth_packed_object_sha1(p, i); - if (!locate_object_entry(sha1)) + if (!locate_object_entry(sha1) && + !has_sha1_pack_kept_or_nonlocal(sha1)) if (force_object_loose(sha1, p->mtime)) die("unable to force loose object"); } @@@ -2200,7 -2173,6 +2224,6 @@@ int cmd_pack_objects(int argc, const ch continue; } if (!strcmp("--unpacked", arg) || - !strcmp("--kept-pack-only", arg) || !strcmp("--reflog", arg) || !strcmp("--all", arg)) { use_internal_rev_list = 1; diff --combined cache.h index f48e80bc05,23c16d0d99..9cf5a13c2c --- a/cache.h +++ b/cache.h @@@ -6,22 -6,12 +6,22 @@@ #include "hash.h" #include SHA1_HEADER -#include +#ifndef git_SHA_CTX +#define git_SHA_CTX SHA_CTX +#define git_SHA1_Init SHA1_Init +#define git_SHA1_Update SHA1_Update +#define git_SHA1_Final SHA1_Final +#endif +#include #if defined(NO_DEFLATE_BOUND) || ZLIB_VERNUM < 0x1200 #define deflateBound(c,s) ((s) + (((s) + 7) >> 3) + (((s) + 63) >> 6) + 11) #endif +void git_inflate_init(z_streamp strm); +void git_inflate_end(z_streamp strm); +int git_inflate(z_streamp strm, int flush); + #if defined(DT_UNKNOWN) && !defined(NO_D_TYPE_IN_DIRENT) #define DTYPE(de) ((de)->d_type) #else @@@ -119,29 -109,9 +119,29 @@@ struct ondisk_cache_entry char name[FLEX_ARRAY]; /* more */ }; +/* + * This struct is used when CE_EXTENDED bit is 1 + * The struct must match ondisk_cache_entry exactly from + * ctime till flags + */ +struct ondisk_cache_entry_extended { + struct cache_time ctime; + struct cache_time mtime; + unsigned int dev; + unsigned int ino; + unsigned int mode; + unsigned int uid; + unsigned int gid; + unsigned int size; + unsigned char sha1[20]; + unsigned short flags; + unsigned short flags2; + char name[FLEX_ARRAY]; /* more */ +}; + struct cache_entry { - unsigned int ce_ctime; - unsigned int ce_mtime; + struct cache_time ce_ctime; + struct cache_time ce_mtime; unsigned int ce_dev; unsigned int ce_ino; unsigned int ce_mode; @@@ -156,19 -126,10 +156,19 @@@ #define CE_NAMEMASK (0x0fff) #define CE_STAGEMASK (0x3000) +#define CE_EXTENDED (0x4000) #define CE_VALID (0x8000) #define CE_STAGESHIFT 12 -/* In-memory only */ +/* + * Range 0xFFFF0000 in ce_flags is divided into + * two parts: in-memory flags and on-disk ones. + * Flags in CE_EXTENDED_FLAGS will get saved on-disk + * if you want to save a new flag, add it in + * CE_EXTENDED_FLAGS + * + * In-memory only flags + */ #define CE_UPDATE (0x10000) #define CE_REMOVE (0x20000) #define CE_UPTODATE (0x40000) @@@ -177,25 -138,6 +177,25 @@@ #define CE_HASHED (0x100000) #define CE_UNHASHED (0x200000) +/* + * Extended on-disk flags + */ +#define CE_INTENT_TO_ADD 0x20000000 +/* CE_EXTENDED2 is for future extension */ +#define CE_EXTENDED2 0x80000000 + +#define CE_EXTENDED_FLAGS (CE_INTENT_TO_ADD) + +/* + * Safeguard to avoid saving wrong flags: + * - CE_EXTENDED2 won't get saved until its semantic is known + * - Bits in 0x0000FFFF have been saved in ce_flags already + * - Bits in 0x003F0000 are currently in-memory flags + */ +#if CE_EXTENDED_FLAGS & 0x803FFFFF +#error "CE_EXTENDED_FLAGS out of range" +#endif + /* * Copy the sha1 and stat state of a cache entry from one to * another. But we never change the name, or the hash state! @@@ -228,9 -170,7 +228,9 @@@ static inline size_t ce_namelen(const s } #define ce_size(ce) cache_entry_size(ce_namelen(ce)) -#define ondisk_ce_size(ce) ondisk_cache_entry_size(ce_namelen(ce)) +#define ondisk_ce_size(ce) (((ce)->ce_flags & CE_EXTENDED) ? \ + ondisk_cache_entry_extended_size(ce_namelen(ce)) : \ + ondisk_cache_entry_size(ce_namelen(ce))) #define ce_stage(ce) ((CE_STAGEMASK & (ce)->ce_flags) >> CE_STAGESHIFT) #define ce_uptodate(ce) ((ce)->ce_flags & CE_UPTODATE) #define ce_mark_uptodate(ce) ((ce)->ce_flags |= CE_UPTODATE) @@@ -273,16 -213,14 +273,16 @@@ static inline int ce_to_dtype(const str (S_ISREG(mode) ? (S_IFREG | ce_permissions(mode)) : \ S_ISLNK(mode) ? S_IFLNK : S_ISDIR(mode) ? S_IFDIR : S_IFGITLINK) -#define cache_entry_size(len) ((offsetof(struct cache_entry,name) + (len) + 8) & ~7) -#define ondisk_cache_entry_size(len) ((offsetof(struct ondisk_cache_entry,name) + (len) + 8) & ~7) +#define flexible_size(STRUCT,len) ((offsetof(struct STRUCT,name) + (len) + 8) & ~7) +#define cache_entry_size(len) flexible_size(cache_entry,len) +#define ondisk_cache_entry_size(len) flexible_size(ondisk_cache_entry,len) +#define ondisk_cache_entry_extended_size(len) flexible_size(ondisk_cache_entry_extended,len) struct index_state { struct cache_entry **cache; unsigned int cache_nr, cache_alloc, cache_changed; struct cache_tree *cache_tree; - time_t timestamp; + struct cache_time timestamp; void *alloc; unsigned name_hash_initialized : 1, initialized : 1; @@@ -317,7 -255,6 +317,7 @@@ static inline void remove_name_hash(str #define read_cache() read_index(&the_index) #define read_cache_from(path) read_index_from(&the_index, (path)) +#define read_cache_preload(pathspec) read_index_preload(&the_index, (pathspec)) #define is_cache_unborn() is_index_unborn(&the_index) #define read_cache_unmerged() read_index_unmerged(&the_index) #define write_cache(newfd, cache, entries) write_index(&the_index, (newfd)) @@@ -377,7 -314,6 +377,7 @@@ extern int is_bare_repository(void) extern int is_inside_git_dir(void); extern char *git_work_tree_cfg; extern int is_inside_work_tree(void); +extern int have_git_dir(void); extern const char *get_git_dir(void); extern char *get_object_directory(void); extern char *get_index_file(void); @@@ -424,11 -360,10 +424,11 @@@ extern int init_db(const char *template /* Initialize and use the cache information */ extern int read_index(struct index_state *); +extern int read_index_preload(struct index_state *, const char **pathspec); extern int read_index_from(struct index_state *, const char *path); extern int is_index_unborn(struct index_state *); extern int read_index_unmerged(struct index_state *); -extern int write_index(const struct index_state *, int newfd); +extern int write_index(struct index_state *, int newfd); extern int discard_index(struct index_state *); extern int unmerged_index(const struct index_state *); extern int verify_path(const char *path); @@@ -438,18 -373,14 +438,18 @@@ extern int index_name_pos(const struct #define ADD_CACHE_OK_TO_REPLACE 2 /* Ok to replace file/directory */ #define ADD_CACHE_SKIP_DFCHECK 4 /* Ok to skip DF conflict checks */ #define ADD_CACHE_JUST_APPEND 8 /* Append only; tree.c::read_tree() */ +#define ADD_CACHE_NEW_ONLY 16 /* Do not replace existing ones */ extern int add_index_entry(struct index_state *, struct cache_entry *ce, int option); extern struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really); extern void rename_index_entry_at(struct index_state *, int pos, const char *new_name); extern int remove_index_entry_at(struct index_state *, int pos); +extern void remove_marked_cache_entries(struct index_state *istate); extern int remove_file_from_index(struct index_state *, const char *path); #define ADD_CACHE_VERBOSE 1 #define ADD_CACHE_PRETEND 2 #define ADD_CACHE_IGNORE_ERRORS 4 +#define ADD_CACHE_IGNORE_REMOVAL 8 +#define ADD_CACHE_INTENT 16 extern int add_to_index(struct index_state *, const char *path, struct stat *, int flags); extern int add_file_to_index(struct index_state *, const char *path, int flags); extern struct cache_entry *make_cache_entry(unsigned int mode, const unsigned char *sha1, const char *path, int stage, int refresh); @@@ -465,6 -396,7 +465,6 @@@ extern int ie_modified(const struct ind extern int ce_path_match(const struct cache_entry *ce, const char **pathspec); extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, enum object_type type, const char *path); -extern int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object); extern int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object); extern void fill_stat_cache_info(struct cache_entry *ce, struct stat *st); @@@ -485,7 -417,6 +485,7 @@@ struct lock_file }; #define LOCK_DIE_ON_ERROR 1 #define LOCK_NODEREF 2 +extern NORETURN void unable_to_lock_index_die(const char *path, int err); extern int hold_lock_file_for_update(struct lock_file *, const char *path, int); extern int hold_lock_file_for_append(struct lock_file *, const char *path, int); extern int commit_lock_file(struct lock_file *); @@@ -517,7 -448,6 +517,7 @@@ extern size_t packed_git_limit extern size_t delta_base_cache_limit; extern int auto_crlf; extern int fsync_object_files; +extern int core_preload_index; enum safe_crlf { SAFE_CRLF_FALSE = 0, @@@ -528,7 -458,6 +528,7 @@@ extern enum safe_crlf safe_crlf; enum branch_track { + BRANCH_TRACK_UNSPECIFIED = -1, BRANCH_TRACK_NEVER = 0, BRANCH_TRACK_REMOTE, BRANCH_TRACK_ALWAYS, @@@ -542,17 -471,8 +542,17 @@@ enum rebase_setup_type AUTOREBASE_ALWAYS, }; +enum push_default_type { + PUSH_DEFAULT_UNSPECIFIED = -1, + PUSH_DEFAULT_NOTHING = 0, + PUSH_DEFAULT_MATCHING, + PUSH_DEFAULT_TRACKING, + PUSH_DEFAULT_CURRENT, +}; + extern enum branch_track git_branch_track; extern enum rebase_setup_type autorebase; +extern enum push_default_type push_default; #define GIT_REPO_VERSION 0 extern int repository_format_version; @@@ -597,13 -517,6 +597,13 @@@ static inline void hashclr(unsigned cha { memset(hash, 0, 20); } +extern int is_empty_blob_sha1(const unsigned char *sha1); + +#define EMPTY_TREE_SHA1_HEX \ + "4b825dc642cb6eb9a060e54bf8d69288fbee4904" +#define EMPTY_TREE_SHA1_BIN \ + "\x4b\x82\x5d\xc6\x42\xcb\x6e\xb9\xa0\x60" \ + "\xe5\x4b\xf8\xd6\x92\x88\xfb\xee\x49\x04" int git_mkstemp(char *path, size_t n, const char *template); @@@ -631,13 -544,11 +631,13 @@@ static inline int is_absolute_path(cons { return path[0] == '/' || has_dos_drive_prefix(path); } +int is_directory(const char *); const char *make_absolute_path(const char *path); const char *make_nonrelative_path(const char *path); const char *make_relative_path(const char *abs, const char *base); -int normalize_absolute_path(char *buf, const char *path); +int normalize_path_copy(char *dst, const char *src); int longest_ancestor_length(const char *path, const char *prefix_list); +char *strip_path_suffix(const char *path, const char *suffix); /* Read and unpack a sha1 file into memory, write memory to a sha1 file */ extern int sha1_object_info(const unsigned char *, unsigned long *); @@@ -647,15 -558,14 +647,14 @@@ extern int write_sha1_file(void *buf, u extern int pretend_sha1_file(void *, unsigned long, enum object_type, unsigned char *); extern int force_object_loose(const unsigned char *sha1, time_t mtime); -/* just like read_sha1_file(), but non fatal in presence of bad objects */ -extern void *read_object(const unsigned char *sha1, enum object_type *type, unsigned long *size); +/* global flag to enable extra checks when accessing packed objects */ +extern int do_check_packed_object_crc; extern int check_sha1_signature(const unsigned char *sha1, void *buf, unsigned long size, const char *type); extern int move_temp_to_file(const char *tmpfile, const char *filename); extern int has_sha1_pack(const unsigned char *sha1); - extern int has_sha1_kept_pack(const unsigned char *sha1); extern int has_sha1_file(const unsigned char *sha1); extern int has_loose_object_nonlocal(const unsigned char *sha1); @@@ -680,7 -590,6 +679,7 @@@ extern int read_ref(const char *filenam extern const char *resolve_ref(const char *path, unsigned char *sha1, int, int *); extern int dwim_ref(const char *str, int len, unsigned char *sha1, char **ref); extern int dwim_log(const char *str, int len, unsigned char *sha1, char **ref); +extern int interpret_nth_last_branch(const char *str, struct strbuf *); extern int refname_match(const char *abbrev_name, const char *full_name, const char **rules); extern const char *ref_rev_parse_rules[]; @@@ -707,8 -616,7 +706,8 @@@ enum date_mode DATE_SHORT, DATE_LOCAL, DATE_ISO8601, - DATE_RFC2822 + DATE_RFC2822, + DATE_RAW }; const char *show_date(unsigned long time, int timezone, enum date_mode mode); @@@ -735,13 -643,7 +734,13 @@@ struct checkout }; extern int checkout_entry(struct cache_entry *ce, const struct checkout *state, char *topath); -extern int has_symlink_leading_path(int len, const char *name); +extern int has_symlink_leading_path(const char *name, int len); +extern int has_symlink_or_noent_leading_path(const char *name, int len); +extern int has_dirs_only_path(const char *name, int len, int prefix_len); +extern void invalidate_lstat_cache(const char *name, int len); +extern void clear_lstat_cache(void); +extern void schedule_dir_for_removal(const char *name, int len); +extern void remove_scheduled_dirs(void); extern struct alternate_object_database { struct alternate_object_database *next; @@@ -750,8 -652,6 +749,8 @@@ } *alt_odb_list; extern void prepare_alt_odb(void); extern void add_to_alternates_file(const char *reference); +typedef int alt_odb_fn(struct alternate_object_database *, void *); +extern void foreach_alt_odb(alt_odb_fn, void*); struct pack_window { struct pack_window *next; @@@ -814,18 -714,14 +813,18 @@@ struct ref #define REF_HEADS (1u << 1) #define REF_TAGS (1u << 2) -extern struct ref *find_ref_by_name(struct ref *list, const char *name); +extern struct ref *find_ref_by_name(const struct ref *list, const char *name); #define CONNECT_VERBOSE (1u << 0) extern struct child_process *git_connect(int fd[2], const char *url, const char *prog, int flags); extern int finish_connect(struct child_process *conn); extern int path_match(const char *path, int nr, char **match); extern int get_ack(int fd, unsigned char *result_sha1); -extern struct ref **get_remote_heads(int in, struct ref **list, int nr_match, char **match, unsigned int flags); +struct extra_have_objects { + int nr, alloc; + unsigned char (*array)[20]; +}; +extern struct ref **get_remote_heads(int in, struct ref **list, int nr_match, char **match, unsigned int flags, struct extra_have_objects *); extern int server_supports(const char *feature); extern struct packed_git *parse_pack_index(unsigned char *sha1); @@@ -843,13 -739,12 +842,13 @@@ extern unsigned char* use_pack(struct p extern void close_pack_windows(struct packed_git *); extern void unuse_pack(struct pack_window **); extern void free_pack_by_name(const char *); +extern void clear_delta_base_cache(void); extern struct packed_git *add_packed_git(const char *, int, int); extern const unsigned char *nth_packed_object_sha1(struct packed_git *, uint32_t); extern off_t nth_packed_object_offset(const struct packed_git *, uint32_t); extern off_t find_pack_entry_one(const unsigned char *, struct packed_git *); extern void *unpack_entry(struct packed_git *, off_t, enum object_type *, unsigned long *); -extern unsigned long unpack_object_header_gently(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep); +extern unsigned long unpack_object_header_buffer(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep); extern unsigned long get_size_from_delta(struct packed_git *, struct pack_window **, off_t); extern const char *packed_object_info_detail(struct packed_git *, off_t, unsigned long *, unsigned long *, unsigned int *, unsigned char *); @@@ -860,6 -755,7 +859,6 @@@ typedef int (*config_fn_t)(const char * extern int git_default_config(const char *, const char *, void *); extern int git_config_from_file(config_fn_t fn, const char *, void *); extern int git_config(config_fn_t fn, void *); -extern int git_parse_long(const char *, long *); extern int git_parse_ulong(const char *, unsigned long *); extern int git_config_int(const char *, const char *); extern unsigned long git_config_ulong(const char *, const char *); @@@ -883,7 -779,6 +882,7 @@@ extern int user_ident_explicitly_given extern const char *git_commit_encoding; extern const char *git_log_output_encoding; +extern const char *git_mailmap_file; /* IO helper functions */ extern void maybe_flush_or_die(FILE *, const char *); @@@ -959,6 -854,7 +958,6 @@@ extern int ws_fix_copy(char *, const ch extern int ws_blank_line(const char *line, int len, unsigned ws_rule); /* ls-files */ -int pathspec_match(const char **spec, char *matched, const char *filename, int skiplen); int report_path_error(const char *ps_matched, const char **pathspec, int prefix_offset); void overlay_tree_on_cache(const char *tree_name, const char *prefix); diff --combined git-repack.sh index 0144c2d7b9,e02bf27aa6..1782a23b26 --- a/git-repack.sh +++ b/git-repack.sh @@@ -71,11 -71,7 +71,7 @@@ case ",$all_into_one," i existing="$existing $e" fi done - if test -n "$existing" - then - args="--kept-pack-only" - fi - if test -n "$args" -a -n "$unpack_unreachable" -a \ + if test -n "$existing" -a -n "$unpack_unreachable" -a \ -n "$remove_redundant" then args="$args $unpack_unreachable" @@@ -92,79 -88,32 +88,79 @@@ if [ -z "$names" ]; the echo Nothing new to pack. fi fi -for name in $names ; do - fullbases="$fullbases pack-$name" - chmod a-w "$PACKTMP-$name.pack" - chmod a-w "$PACKTMP-$name.idx" - mkdir -p "$PACKDIR" || exit +# Ok we have prepared all new packfiles. +mkdir -p "$PACKDIR" || exit + +# First see if there are packs of the same name and if so +# if we can move them out of the way (this can happen if we +# repacked immediately after packing fully. +rollback= +failed= +for name in $names +do for sfx in pack idx do - if test -f "$PACKDIR/pack-$name.$sfx" - then - mv -f "$PACKDIR/pack-$name.$sfx" \ - "$PACKDIR/old-pack-$name.$sfx" - fi - done && + file=pack-$name.$sfx + test -f "$PACKDIR/$file" || continue + rm -f "$PACKDIR/old-$file" && + mv "$PACKDIR/$file" "$PACKDIR/old-$file" || { + failed=t + break + } + rollback="$rollback $file" + done + test -z "$failed" || break +done + +# If renaming failed for any of them, roll the ones we have +# already renamed back to their original names. +if test -n "$failed" +then + rollback_failure= + for file in $rollback + do + mv "$PACKDIR/old-$file" "$PACKDIR/$file" || + rollback_failure="$rollback_failure $file" + done + if test -n "$rollback_failure" + then + echo >&2 "WARNING: Some packs in use have been renamed by" + echo >&2 "WARNING: prefixing old- to their name, in order to" + echo >&2 "WARNING: replace them with the new version of the" + echo >&2 "WARNING: file. But the operation failed, and" + echo >&2 "WARNING: attempt to rename them back to their" + echo >&2 "WARNING: original names also failed." + echo >&2 "WARNING: Please rename them in $PACKDIR manually:" + for file in $rollback_failure + do + echo >&2 "WARNING: old-$file -> $file" + done + fi + exit 1 +fi + +# Now the ones with the same name are out of the way... +fullbases= +for name in $names +do + fullbases="$fullbases pack-$name" + chmod a-w "$PACKTMP-$name.pack" + chmod a-w "$PACKTMP-$name.idx" mv -f "$PACKTMP-$name.pack" "$PACKDIR/pack-$name.pack" && - mv -f "$PACKTMP-$name.idx" "$PACKDIR/pack-$name.idx" && - test -f "$PACKDIR/pack-$name.pack" && - test -f "$PACKDIR/pack-$name.idx" || { - echo >&2 "Couldn't replace the existing pack with updated one." - echo >&2 "The original set of packs have been saved as" - echo >&2 "old-pack-$name.{pack,idx} in $PACKDIR." - exit 1 - } - rm -f "$PACKDIR/old-pack-$name.pack" "$PACKDIR/old-pack-$name.idx" + mv -f "$PACKTMP-$name.idx" "$PACKDIR/pack-$name.idx" || + exit +done + +# Remove the "old-" files +for name in $names +do + rm -f "$PACKDIR/old-pack-$name.idx" + rm -f "$PACKDIR/old-pack-$name.pack" done +# End of pack replacement. + if test "$remove_redundant" = t then # We know $existing are all redundant. diff --combined revision.c index f5771c7898,50a5b5f394..b6215cc72c --- a/revision.c +++ b/revision.c @@@ -11,7 -11,6 +11,7 @@@ #include "reflog-walk.h" #include "patch-ids.h" #include "decorate.h" +#include "log-tree.h" volatile show_early_output_fn_t show_early_output; @@@ -183,11 -182,8 +183,11 @@@ static struct commit *handle_commit(str if (!tag->tagged) die("bad tag"); object = parse_object(tag->tagged->sha1); - if (!object) + if (!object) { + if (flags & UNINTERESTING) + return NULL; die("bad object %s", sha1_to_hex(tag->tagged->sha1)); + } } /* @@@ -203,8 -199,6 +203,8 @@@ mark_parents_uninteresting(commit); revs->limited = 1; } + if (revs->show_source && !commit->util) + commit->util = (void *) name; return commit; } @@@ -298,31 -292,10 +298,31 @@@ static void file_change(struct diff_opt DIFF_OPT_SET(options, HAS_CHANGES); } -static int rev_compare_tree(struct rev_info *revs, struct tree *t1, struct tree *t2) +static int rev_compare_tree(struct rev_info *revs, struct commit *parent, struct commit *commit) { + struct tree *t1 = parent->tree; + struct tree *t2 = commit->tree; + if (!t1) return REV_TREE_NEW; + + if (revs->simplify_by_decoration) { + /* + * If we are simplifying by decoration, then the commit + * is worth showing if it has a tag pointing at it. + */ + if (lookup_decoration(&name_decoration, &commit->object)) + return REV_TREE_DIFFERENT; + /* + * A commit that is not pointed by a tag is uninteresting + * if we are not limited by path. This means that you will + * see the usual "commits that touch the paths" plus any + * tagged commit by specifying both --simplify-by-decoration + * and pathspec. + */ + if (!revs->prune_data) + return REV_TREE_SAME; + } if (!t2) return REV_TREE_DIFFERENT; tree_difference = REV_TREE_SAME; @@@ -333,13 -306,12 +333,13 @@@ return tree_difference; } -static int rev_same_tree_as_empty(struct rev_info *revs, struct tree *t1) +static int rev_same_tree_as_empty(struct rev_info *revs, struct commit *commit) { int retval; void *tree; unsigned long size; struct tree_desc empty, real; + struct tree *t1 = commit->tree; if (!t1) return 0; @@@ -373,7 -345,7 +373,7 @@@ static void try_to_simplify_commit(stru return; if (!commit->parents) { - if (rev_same_tree_as_empty(revs, commit->tree)) + if (rev_same_tree_as_empty(revs, commit)) commit->object.flags |= TREESAME; return; } @@@ -393,7 -365,7 +393,7 @@@ die("cannot simplify commit %s (because of %s)", sha1_to_hex(commit->object.sha1), sha1_to_hex(p->object.sha1)); - switch (rev_compare_tree(revs, p->tree, commit->tree)) { + switch (rev_compare_tree(revs, p, commit)) { case REV_TREE_SAME: tree_same = 1; if (!revs->simplify_history || (p->object.flags & UNINTERESTING)) { @@@ -413,7 -385,7 +413,7 @@@ case REV_TREE_NEW: if (revs->remove_empty_trees && - rev_same_tree_as_empty(revs, p->tree)) { + rev_same_tree_as_empty(revs, p)) { /* We are adding all the specified * paths from this parent, so the * history beyond this parent is not @@@ -482,10 -454,9 +482,10 @@@ static int add_parents_to_list(struct r while (parent) { struct commit *p = parent->item; parent = parent->next; + if (p) + p->object.flags |= UNINTERESTING; if (parse_commit(p) < 0) - return -1; - p->object.flags |= UNINTERESTING; + continue; if (p->parents) mark_parents_uninteresting(p); if (p->object.flags & SEEN) @@@ -513,14 -484,12 +513,14 @@@ if (parse_commit(p) < 0) return -1; + if (revs->show_source && !p->util) + p->util = commit->util; p->object.flags |= left_flag; if (!(p->object.flags & SEEN)) { p->object.flags |= SEEN; insert_by_date_cached(p, list, cached_base, cache_ptr); } - if(revs->first_parent_only) + if (revs->first_parent_only) break; } return 0; @@@ -1049,19 -1018,6 +1049,19 @@@ static int handle_revision_opt(struct r } else if (!strcmp(arg, "--topo-order")) { revs->lifo = 1; revs->topo_order = 1; + } else if (!strcmp(arg, "--simplify-merges")) { + revs->simplify_merges = 1; + revs->rewrite_parents = 1; + revs->simplify_history = 0; + revs->limited = 1; + } else if (!strcmp(arg, "--simplify-by-decoration")) { + revs->simplify_merges = 1; + revs->rewrite_parents = 1; + revs->simplify_history = 0; + revs->simplify_by_decoration = 1; + revs->limited = 1; + revs->prune = 1; + load_ref_decorations(); } else if (!strcmp(arg, "--date-order")) { revs->lifo = 0; revs->topo_order = 1; @@@ -1106,10 -1062,6 +1106,6 @@@ revs->edge_hint = 1; } else if (!strcmp(arg, "--unpacked")) { revs->unpacked = 1; - revs->kept_pack_only = 0; - } else if (!strcmp(arg, "--kept-pack-only")) { - revs->unpacked = 1; - revs->kept_pack_only = 1; } else if (!prefixcmp(arg, "--unpacked=")) { die("--unpacked= no longer supported."); } else if (!strcmp(arg, "-r")) { @@@ -1134,13 -1086,9 +1130,13 @@@ } else if (!strcmp(arg, "--pretty")) { revs->verbose_header = 1; get_commit_format(arg+8, revs); - } else if (!prefixcmp(arg, "--pretty=")) { + } else if (!prefixcmp(arg, "--pretty=") || !prefixcmp(arg, "--format=")) { revs->verbose_header = 1; get_commit_format(arg+9, revs); + } else if (!strcmp(arg, "--oneline")) { + revs->verbose_header = 1; + get_commit_format("oneline", revs); + revs->abbrev_commit = 1; } else if (!strcmp(arg, "--graph")) { revs->topo_order = 1; revs->rewrite_parents = 1; @@@ -1261,7 -1209,6 +1257,7 @@@ int setup_revisions(int argc, const cha if (!strcmp(arg, "--all")) { handle_refs(revs, flags, for_each_ref); + handle_refs(revs, flags, head_ref); continue; } if (!strcmp(arg, "--branches")) { @@@ -1394,179 -1341,6 +1390,179 @@@ static void add_child(struct rev_info * l->next = add_decoration(&revs->children, &parent->object, l); } +static int remove_duplicate_parents(struct commit *commit) +{ + struct commit_list **pp, *p; + int surviving_parents; + + /* Examine existing parents while marking ones we have seen... */ + pp = &commit->parents; + while ((p = *pp) != NULL) { + struct commit *parent = p->item; + if (parent->object.flags & TMP_MARK) { + *pp = p->next; + continue; + } + parent->object.flags |= TMP_MARK; + pp = &p->next; + } + /* count them while clearing the temporary mark */ + surviving_parents = 0; + for (p = commit->parents; p; p = p->next) { + p->item->object.flags &= ~TMP_MARK; + surviving_parents++; + } + return surviving_parents; +} + +struct merge_simplify_state { + struct commit *simplified; +}; + +static struct merge_simplify_state *locate_simplify_state(struct rev_info *revs, struct commit *commit) +{ + struct merge_simplify_state *st; + + st = lookup_decoration(&revs->merge_simplification, &commit->object); + if (!st) { + st = xcalloc(1, sizeof(*st)); + add_decoration(&revs->merge_simplification, &commit->object, st); + } + return st; +} + +static struct commit_list **simplify_one(struct rev_info *revs, struct commit *commit, struct commit_list **tail) +{ + struct commit_list *p; + struct merge_simplify_state *st, *pst; + int cnt; + + st = locate_simplify_state(revs, commit); + + /* + * Have we handled this one? + */ + if (st->simplified) + return tail; + + /* + * An UNINTERESTING commit simplifies to itself, so does a + * root commit. We do not rewrite parents of such commit + * anyway. + */ + if ((commit->object.flags & UNINTERESTING) || !commit->parents) { + st->simplified = commit; + return tail; + } + + /* + * Do we know what commit all of our parents should be rewritten to? + * Otherwise we are not ready to rewrite this one yet. + */ + for (cnt = 0, p = commit->parents; p; p = p->next) { + pst = locate_simplify_state(revs, p->item); + if (!pst->simplified) { + tail = &commit_list_insert(p->item, tail)->next; + cnt++; + } + } + if (cnt) { + tail = &commit_list_insert(commit, tail)->next; + return tail; + } + + /* + * Rewrite our list of parents. + */ + for (p = commit->parents; p; p = p->next) { + pst = locate_simplify_state(revs, p->item); + p->item = pst->simplified; + } + cnt = remove_duplicate_parents(commit); + + /* + * It is possible that we are a merge and one side branch + * does not have any commit that touches the given paths; + * in such a case, the immediate parents will be rewritten + * to different commits. + * + * o----X X: the commit we are looking at; + * / / o: a commit that touches the paths; + * ---o----' + * + * Further reduce the parents by removing redundant parents. + */ + if (1 < cnt) { + struct commit_list *h = reduce_heads(commit->parents); + cnt = commit_list_count(h); + free_commit_list(commit->parents); + commit->parents = h; + } + + /* + * A commit simplifies to itself if it is a root, if it is + * UNINTERESTING, if it touches the given paths, or if it is a + * merge and its parents simplifies to more than one commits + * (the first two cases are already handled at the beginning of + * this function). + * + * Otherwise, it simplifies to what its sole parent simplifies to. + */ + if (!cnt || + (commit->object.flags & UNINTERESTING) || + !(commit->object.flags & TREESAME) || + (1 < cnt)) + st->simplified = commit; + else { + pst = locate_simplify_state(revs, commit->parents->item); + st->simplified = pst->simplified; + } + return tail; +} + +static void simplify_merges(struct rev_info *revs) +{ + struct commit_list *list; + struct commit_list *yet_to_do, **tail; + + if (!revs->topo_order) + sort_in_topological_order(&revs->commits, revs->lifo); + if (!revs->prune) + return; + + /* feed the list reversed */ + yet_to_do = NULL; + for (list = revs->commits; list; list = list->next) + commit_list_insert(list->item, &yet_to_do); + while (yet_to_do) { + list = yet_to_do; + yet_to_do = NULL; + tail = &yet_to_do; + while (list) { + struct commit *commit = list->item; + struct commit_list *next = list->next; + free(list); + list = next; + tail = simplify_one(revs, commit, tail); + } + } + + /* clean up the result, removing the simplified ones */ + list = revs->commits; + revs->commits = NULL; + tail = &revs->commits; + while (list) { + struct commit *commit = list->item; + struct commit_list *next = list->next; + struct merge_simplify_state *st; + free(list); + list = next; + st = locate_simplify_state(revs, commit); + if (st->simplified == commit) + tail = &commit_list_insert(commit, tail)->next; + } +} + static void set_children(struct rev_info *revs) { struct commit_list *l; @@@ -1607,8 -1381,6 +1603,8 @@@ int prepare_revision_walk(struct rev_in return -1; if (revs->topo_order) sort_in_topological_order(&revs->commits, revs->lifo); + if (revs->simplify_merges) + simplify_merges(revs); if (revs->children.name) set_children(revs); return 0; @@@ -1641,6 -1413,26 +1637,6 @@@ static enum rewrite_result rewrite_one( } } -static void remove_duplicate_parents(struct commit *commit) -{ - struct commit_list **pp, *p; - - /* Examine existing parents while marking ones we have seen... */ - pp = &commit->parents; - while ((p = *pp) != NULL) { - struct commit *parent = p->item; - if (parent->object.flags & TMP_MARK) { - *pp = p->next; - continue; - } - parent->object.flags |= TMP_MARK; - pp = &p->next; - } - /* ... and clear the temporary mark */ - for (p = commit->parents; p; p = p->next) - p->item->object.flags &= ~TMP_MARK; -} - static int rewrite_parents(struct rev_info *revs, struct commit *commit) { struct commit_list **pp = &commit->parents; @@@ -1679,10 -1471,7 +1675,7 @@@ enum commit_action simplify_commit(stru { if (commit->object.flags & SHOWN) return commit_ignore; - if (revs->unpacked && - (revs->kept_pack_only - ? has_sha1_kept_pack(commit->object.sha1) - : has_sha1_pack(commit->object.sha1))) + if (revs->unpacked && has_sha1_pack(commit->object.sha1)) return commit_ignore; if (revs->show_all) return commit_show; @@@ -1735,16 -1524,14 +1728,16 @@@ static struct commit *get_revision_1(st (commit->date < revs->max_age)) continue; if (add_parents_to_list(revs, commit, &revs->commits, NULL) < 0) - return NULL; + die("Failed to traverse parents of commit %s", + sha1_to_hex(commit->object.sha1)); } switch (simplify_commit(revs, commit)) { case commit_ignore: continue; case commit_error: - return NULL; + die("Failed to simplify parents of commit %s", + sha1_to_hex(commit->object.sha1)); default: return commit; } @@@ -1832,6 -1619,26 +1825,6 @@@ static struct commit *get_revision_inte return c; } - if (revs->reverse) { - int limit = -1; - - if (0 <= revs->max_count) { - limit = revs->max_count; - if (0 < revs->skip_count) - limit += revs->skip_count; - } - l = NULL; - while ((c = get_revision_1(revs))) { - commit_list_insert(c, &l); - if ((0 < limit) && !--limit) - break; - } - revs->commits = l; - revs->reverse = 0; - revs->max_count = -1; - c = NULL; - } - /* * Now pick up what they want to give us */ @@@ -1904,23 -1711,7 +1897,23 @@@ struct commit *get_revision(struct rev_info *revs) { - struct commit *c = get_revision_internal(revs); + struct commit *c; + struct commit_list *reversed; + + if (revs->reverse) { + reversed = NULL; + while ((c = get_revision_internal(revs))) { + commit_list_insert(c, &reversed); + } + revs->commits = reversed; + revs->reverse = 0; + revs->reverse_output_stage = 1; + } + + if (revs->reverse_output_stage) + return pop_commit(&revs->commits); + + c = get_revision_internal(revs); if (c && revs->graph) graph_update(revs->graph, c); return c; diff --combined revision.h index ad123d78c5,1d322759aa..6e98b71b49 --- a/revision.h +++ b/revision.h @@@ -42,23 -42,17 +42,22 @@@ struct rev_info simplify_history:1, lifo:1, topo_order:1, + simplify_merges:1, + simplify_by_decoration:1, tag_objects:1, tree_objects:1, blob_objects:1, edge_hint:1, limited:1, unpacked:1, - kept_pack_only:1, boundary:2, left_right:1, rewrite_parents:1, print_parents:1, + show_source:1, + show_decorations:1, reverse:1, + reverse_output_stage:1, cherry_pick:1, first_parent_only:1; @@@ -87,7 -81,7 +86,7 @@@ int nr, total; const char *mime_boundary; char *message_id; - const char *ref_message_id; + struct string_list *ref_message_ids; const char *add_signoff; const char *extra_headers; const char *log_reencode; @@@ -113,7 -107,6 +112,7 @@@ struct reflog_walk_info *reflog_info; struct decoration children; + struct decoration merge_simplification; }; #define REV_TREE_SAME 0 diff --combined sha1_file.c index 54972f97e0,500fd93127..37e833b77d --- a/sha1_file.c +++ b/sha1_file.c @@@ -99,11 -99,7 +99,11 @@@ int safe_create_leading_directories(cha pos = strchr(pos, '/'); if (!pos) break; - *pos = 0; + while (*++pos == '/') + ; + if (!*pos) + break; + *--pos = '\0'; if (!stat(path, &st)) { /* path exists */ if (!S_ISDIR(st.st_mode)) { @@@ -254,6 -250,7 +254,6 @@@ static void read_info_alternates(const */ static int link_alt_odb_entry(const char * entry, int len, const char * relative_base, int depth) { - struct stat st; const char *objdir = get_object_directory(); struct alternate_object_database *ent; struct alternate_object_database *alt; @@@ -284,7 -281,7 +284,7 @@@ ent->base[pfxlen] = ent->base[entlen-1] = 0; /* Detect cases where alternate disappeared */ - if (stat(ent->base, &st) || !S_ISDIR(st.st_mode)) { + if (!is_directory(ent->base)) { error("object directory %s does not exist; " "check .git/objects/info/alternates.", ent->base); @@@ -397,16 -394,6 +397,16 @@@ void add_to_alternates_file(const char link_alt_odb_entries(alt, alt + strlen(alt), '\n', NULL, 0); } +void foreach_alt_odb(alt_odb_fn fn, void *cb) +{ + struct alternate_object_database *ent; + + prepare_alt_odb(); + for (ent = alt_odb_list; ent; ent = ent->next) + if (fn(ent, cb)) + return; +} + void prepare_alt_odb(void) { const char *alt; @@@ -689,7 -676,6 +689,7 @@@ void free_pack_by_name(const char *pack while (*pp) { p = *pp; if (strcmp(pack_name, p->pack_name) == 0) { + clear_delta_base_cache(); close_pack_windows(p); if (p->pack_fd != -1) close(p->pack_fd); @@@ -801,7 -787,7 +801,7 @@@ unsigned char* use_pack(struct packed_g 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 + /* Since packfiles end in a hash of their content and it's * 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. @@@ -1154,8 -1140,7 +1154,8 @@@ static int legacy_loose_object(unsigne return 0; } -unsigned long unpack_object_header_gently(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep) +unsigned long unpack_object_header_buffer(const unsigned char *buf, + unsigned long len, enum object_type *type, unsigned long *sizep) { unsigned shift; unsigned char c; @@@ -1167,10 -1152,10 +1167,10 @@@ size = c & 15; shift = 4; while (c & 0x80) { - if (len <= used) - return 0; - if (sizeof(long) * 8 <= shift) + if (len <= used || sizeof(long) * 8 <= shift) { + error("bad object header"); return 0; + } c = buf[used++]; size += (c & 0x7f) << shift; shift += 7; @@@ -1197,8 -1182,8 +1197,8 @@@ static int unpack_sha1_header(z_stream stream->avail_out = bufsiz; if (legacy_loose_object(map)) { - inflateInit(stream); - return inflate(stream, 0); + git_inflate_init(stream); + return git_inflate(stream, 0); } @@@ -1209,7 -1194,7 +1209,7 @@@ * 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); + used = unpack_object_header_buffer(map, mapsize, &type, &size); if (!used || !valid_loose_object_type[type]) return -1; map += used; @@@ -1218,7 -1203,7 +1218,7 @@@ /* Set up the stream for the rest.. */ stream->next_in = map; stream->avail_in = mapsize; - inflateInit(stream); + git_inflate_init(stream); /* And generate the fake traditional header */ stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu", @@@ -1255,11 -1240,11 +1255,11 @@@ static void *unpack_sha1_rest(z_stream stream->next_out = buf + bytes; stream->avail_out = size - bytes; while (status == Z_OK) - status = inflate(stream, Z_FINISH); + status = git_inflate(stream, Z_FINISH); } buf[size] = 0; if (status == Z_STREAM_END && !stream->avail_in) { - inflateEnd(stream); + git_inflate_end(stream); return buf; } @@@ -1349,19 -1334,17 +1349,19 @@@ unsigned long get_size_from_delta(struc stream.next_out = delta_head; stream.avail_out = sizeof(delta_head); - inflateInit(&stream); + git_inflate_init(&stream); do { in = use_pack(p, w_curs, curpos, &stream.avail_in); stream.next_in = in; - st = inflate(&stream, Z_FINISH); + 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)); - inflateEnd(&stream); - if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) - die("delta data unpack-initial failed"); + 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. @@@ -1402,7 -1385,7 +1402,7 @@@ static off_t get_delta_base(struct pack base_offset = (base_offset << 7) + (c & 127); } base_offset = delta_obj_offset - base_offset; - if (base_offset >= delta_obj_offset) + if (base_offset <= 0 || base_offset >= delta_obj_offset) return 0; /* out of bound */ *curpos += used; } else if (type == OBJ_REF_DELTA) { @@@ -1428,32 -1411,15 +1428,32 @@@ static int packed_delta_info(struct pac off_t base_offset; base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset); + if (!base_offset) + return OBJ_BAD; type = packed_object_info(p, base_offset, NULL); + if (type <= OBJ_NONE) { + struct revindex_entry *revidx; + const unsigned char *base_sha1; + revidx = find_pack_revindex(p, base_offset); + if (!revidx) + return OBJ_BAD; + base_sha1 = nth_packed_object_sha1(p, revidx->nr); + mark_bad_packed_object(p, base_sha1); + type = sha1_object_info(base_sha1, NULL); + if (type <= OBJ_NONE) + return OBJ_BAD; + } /* 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 (sizep) + if (sizep) { *sizep = get_size_from_delta(p, w_curs, curpos); + if (*sizep == 0) + type = OBJ_BAD; + } return type; } @@@ -1475,11 -1441,10 +1475,11 @@@ static int unpack_object_header(struct * 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; + used = unpack_object_header_buffer(base, left, &type, sizep); + if (!used) { + type = OBJ_BAD; + } else + *curpos += used; return type; } @@@ -1563,9 -1528,8 +1563,9 @@@ static int packed_object_info(struct pa *sizep = size; break; default: - die("pack %s contains unknown object type %d", - p->pack_name, type); + error("unknown object type %i at offset %"PRIuMAX" in %s", + type, (uintmax_t)obj_offset, p->pack_name); + type = OBJ_BAD; } unuse_pack(&w_curs); return type; @@@ -1586,14 -1550,14 +1586,14 @@@ static void *unpack_compressed_entry(st stream.next_out = buffer; stream.avail_out = size; - inflateInit(&stream); + git_inflate_init(&stream); do { in = use_pack(p, w_curs, curpos, &stream.avail_in); stream.next_in = in; - st = inflate(&stream, Z_FINISH); + st = git_inflate(&stream, Z_FINISH); curpos += stream.next_in - in; } while (st == Z_OK || st == Z_BUF_ERROR); - inflateEnd(&stream); + git_inflate_end(&stream); if ((st != Z_STREAM_END) || stream.total_out != size) { free(buffer); return NULL; @@@ -1637,9 -1601,11 +1637,9 @@@ static void *cache_or_unpack_entry(stru 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); + if (!ret || ent->p != p || ent->base_offset != base_offset) + 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; @@@ -1664,13 -1630,6 +1664,13 @@@ static inline void release_delta_base_c } } +void clear_delta_base_cache(void) +{ + unsigned long p; + for (p = 0; p < MAX_DELTA_CACHE; p++) + release_delta_base_cache(&delta_base_cache[p]); +} + static void add_delta_base_cache(struct packed_git *p, off_t base_offset, void *base, unsigned long base_size, enum object_type type) { @@@ -1708,9 -1667,6 +1708,9 @@@ delta_base_cache_lru.prev = &ent->lru; } +static void *read_object(const unsigned char *sha1, enum object_type *type, + unsigned long *size); + static void *unpack_delta_entry(struct packed_git *p, struct pack_window **w_curs, off_t curpos, @@@ -1739,12 -1695,9 +1739,12 @@@ * This is costly but should happen only in the presence * of a corrupted pack, and is better than failing outright. */ - struct revindex_entry *revidx = find_pack_revindex(p, base_offset); - const unsigned char *base_sha1 = - nth_packed_object_sha1(p, revidx->nr); + struct revindex_entry *revidx; + const unsigned char *base_sha1; + revidx = find_pack_revindex(p, base_offset); + if (!revidx) + return NULL; + 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)base_offset, @@@ -1773,8 -1726,6 +1773,8 @@@ return result; } +int do_check_packed_object_crc; + void *unpack_entry(struct packed_git *p, off_t obj_offset, enum object_type *type, unsigned long *sizep) { @@@ -1782,20 -1733,6 +1782,20 @@@ off_t curpos = obj_offset; void *data; + if (do_check_packed_object_crc && p->index_version > 1) { + struct revindex_entry *revidx = find_pack_revindex(p, obj_offset); + unsigned long 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); + unuse_pack(&w_curs); + return NULL; + } + } + *type = unpack_object_header(p, &w_curs, &curpos, sizep); switch (*type) { case OBJ_OFS_DELTA: @@@ -1919,8 -1856,7 +1919,7 @@@ off_t find_pack_entry_one(const unsigne return 0; } - static int find_pack_ent(const unsigned char *sha1, struct pack_entry *e, - int kept_pack_only) + static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e) { static struct packed_git *last_found = (void *)1; struct packed_git *p; @@@ -1932,8 -1868,6 +1931,6 @@@ p = (last_found == (void *)1) ? packed_git : last_found; do { - if (kept_pack_only && !p->pack_keep) - goto next; if (p->num_bad_objects) { unsigned i; for (i = 0; i < p->num_bad_objects; i++) @@@ -1973,16 -1907,6 +1970,6 @@@ return 0; } - static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e) - { - return find_pack_ent(sha1, e, 0); - } - - static int find_kept_pack_entry(const unsigned char *sha1, struct pack_entry *e) - { - return find_pack_ent(sha1, e, 1); - } - struct packed_git *find_sha1_pack(const unsigned char *sha1, struct packed_git *packs) { @@@ -2014,7 -1938,7 +2001,7 @@@ static int sha1_loose_object_info(cons status = error("unable to parse %s header", sha1_to_hex(sha1)); else if (sizep) *sizep = size; - inflateEnd(&stream); + git_inflate_end(&stream); munmap(map, mapsize); return status; } @@@ -2035,14 -1959,7 +2022,14 @@@ int sha1_object_info(const unsigned cha if (!find_pack_entry(sha1, &e)) return status; } - return packed_object_info(e.p, e.offset, sizep); + + status = packed_object_info(e.p, e.offset, sizep); + if (status < 0) { + mark_bad_packed_object(e.p, sha1); + status = sha1_object_info(sha1, sizep); + } + + return status; } static void *read_packed_sha1(const unsigned char *sha1, @@@ -2084,7 -2001,9 +2071,7 @@@ static struct cached_object static int cached_object_nr, cached_object_alloc; static struct cached_object empty_tree = { - /* empty tree sha1: 4b825dc642cb6eb9a060e54bf8d69288fbee4904 */ - "\x4b\x82\x5d\xc6\x42\xcb\x6e\xb9\xa0\x60" - "\xe5\x4b\xf8\xd6\x92\x88\xfb\xee\x49\x04", + EMPTY_TREE_SHA1_BIN, OBJ_TREE, "", 0 @@@ -2127,8 -2046,8 +2114,8 @@@ int pretend_sha1_file(void *buf, unsign return 0; } -void *read_object(const unsigned char *sha1, enum object_type *type, - unsigned long *size) +static void *read_object(const unsigned char *sha1, enum object_type *type, + unsigned long *size) { unsigned long mapsize; void *map, *buf; @@@ -2216,16 -2135,16 +2203,16 @@@ static void write_sha1_file_prepare(con const char *type, unsigned char *sha1, char *hdr, int *hdrlen) { - SHA_CTX c; + git_SHA_CTX c; /* Generate the header */ *hdrlen = sprintf(hdr, "%s %lu", type, len)+1; /* Sha1.. */ - SHA1_Init(&c); - SHA1_Update(&c, hdr, *hdrlen); - SHA1_Update(&c, buf, len); - SHA1_Final(sha1, &c); + git_SHA1_Init(&c); + git_SHA1_Update(&c, hdr, *hdrlen); + git_SHA1_Update(&c, buf, len); + git_SHA1_Final(sha1, &c); } /* @@@ -2287,7 -2206,7 +2274,7 @@@ static void close_sha1_file(int fd fsync_or_die(fd, "sha1 file"); fchmod(fd, 0444); if (close(fd) != 0) - die("unable to write sha1 file"); + die("error when closing sha1 file (%s)", strerror(errno)); } /* Size of directory component, including the ending '/' */ @@@ -2334,8 -2253,7 +2321,8 @@@ static int create_tmpfile(char *buffer static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen, void *buf, unsigned long len, time_t mtime) { - int fd, size, ret; + int fd, ret; + size_t size; unsigned char *compressed; z_stream stream; char *filename; @@@ -2456,12 -2374,6 +2443,6 @@@ int has_sha1_pack(const unsigned char * return find_pack_entry(sha1, &e); } - int has_sha1_kept_pack(const unsigned char *sha1) - { - struct pack_entry e; - return find_kept_pack_entry(sha1, &e); - } - int has_sha1_file(const unsigned char *sha1) { struct pack_entry e; @@@ -2471,21 -2383,51 +2452,21 @@@ return has_loose_object(sha1); } -int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object) -{ - struct strbuf buf; - int ret; - - strbuf_init(&buf, 0); - if (strbuf_read(&buf, fd, 4096) < 0) { - strbuf_release(&buf); - return -1; - } - - if (!type) - type = blob_type; - if (write_object) - ret = write_sha1_file(buf.buf, buf.len, type, sha1); - else - ret = hash_sha1_file(buf.buf, buf.len, type, sha1); - strbuf_release(&buf); - - return ret; -} - -int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, - enum object_type type, const char *path) +static int index_mem(unsigned char *sha1, void *buf, size_t size, + int write_object, enum object_type type, const char *path) { - size_t size = xsize_t(st->st_size); - void *buf = NULL; int ret, re_allocated = 0; - if (size) - buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); - close(fd); - if (!type) type = OBJ_BLOB; /* * Convert blobs to git internal format */ - if ((type == OBJ_BLOB) && S_ISREG(st->st_mode)) { - struct strbuf nbuf; - strbuf_init(&nbuf, 0); + if ((type == OBJ_BLOB) && path) { + struct strbuf nbuf = STRBUF_INIT; if (convert_to_git(path, buf, size, &nbuf, write_object ? safe_crlf : 0)) { - munmap(buf, size); buf = strbuf_detach(&nbuf, &size); re_allocated = 1; } @@@ -2495,39 -2437,20 +2476,39 @@@ ret = write_sha1_file(buf, size, typename(type), sha1); else ret = hash_sha1_file(buf, size, typename(type), sha1); - if (re_allocated) { + if (re_allocated) free(buf); - return ret; - } - if (size) + return ret; +} + +int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, + enum object_type type, const char *path) +{ + int ret; + size_t size = xsize_t(st->st_size); + + if (!S_ISREG(st->st_mode)) { + struct strbuf sbuf = STRBUF_INIT; + if (strbuf_read(&sbuf, fd, 4096) >= 0) + ret = index_mem(sha1, sbuf.buf, sbuf.len, write_object, + type, path); + else + ret = -1; + strbuf_release(&sbuf); + } else if (size) { + void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); + ret = index_mem(sha1, buf, size, write_object, type, path); munmap(buf, size); + } else + ret = index_mem(sha1, NULL, size, write_object, type, path); + close(fd); return ret; } int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object) { int fd; - char *target; - size_t len; + struct strbuf sb = STRBUF_INIT; switch (st->st_mode & S_IFMT) { case S_IFREG: @@@ -2540,17 -2463,20 +2521,17 @@@ path); break; case S_IFLNK: - len = xsize_t(st->st_size); - target = xmalloc(len + 1); - if (readlink(path, target, len + 1) != st->st_size) { + if (strbuf_readlink(&sb, path, st->st_size)) { char *errstr = strerror(errno); - free(target); return error("readlink(\"%s\"): %s", path, errstr); } if (!write_object) - hash_sha1_file(target, len, blob_type, sha1); - else if (write_sha1_file(target, len, blob_type, sha1)) + hash_sha1_file(sb.buf, sb.len, blob_type, sha1); + else if (write_sha1_file(sb.buf, sb.len, blob_type, sha1)) return error("%s: failed to insert into database", path); - free(target); + strbuf_release(&sb); break; case S_IFDIR: return resolve_gitlink_ref(path, "HEAD", sha1); diff --combined t/t7700-repack.sh index f5682d66db,9ce546e3b2..6b29bff782 --- a/t/t7700-repack.sh +++ b/t/t7700-repack.sh @@@ -69,24 -69,66 +69,85 @@@ test_expect_success 'packed obs in alt done ' +test_expect_failure 'packed obs in alt ODB are repacked when local repo has packs' ' + rm -f .git/objects/pack/* && + echo new_content >> file1 && + git add file1 && + git commit -m more_content && + git repack && + git repack -a -d && + myidx=$(ls -1 .git/objects/pack/*.idx) && + test -f "$myidx" && + for p in alt_objects/pack/*.idx; do + git verify-pack -v $p | sed -n -e "/^[0-9a-f]\{40\}/p" + done | while read sha1 rest; do + if ! ( git verify-pack -v $myidx | grep "^$sha1" ); then + echo "Missing object in local pack: $sha1" + return 1 + fi + done +' + + test_expect_success 'packed obs in alternate ODB kept pack are repacked' ' + # swap the .keep so the commit object is in the pack with .keep + for p in alt_objects/pack/*.pack + do + base_name=$(basename $p .pack) + if test -f alt_objects/pack/$base_name.keep + then + rm alt_objects/pack/$base_name.keep + else + touch alt_objects/pack/$base_name.keep + fi + done + git repack -a -d && + myidx=$(ls -1 .git/objects/pack/*.idx) && + test -f "$myidx" && + for p in alt_objects/pack/*.idx; do + git verify-pack -v $p | sed -n -e "/^[0-9a-f]\{40\}/p" + done | while read sha1 rest; do + if ! ( git verify-pack -v $myidx | grep "^$sha1" ); then + echo "Missing object in local pack: $sha1" + return 1 + fi + done + ' + + test_expect_success 'packed unreachable obs in alternate ODB are not loosened' ' + rm -f alt_objects/pack/*.keep && + mv .git/objects/pack/* alt_objects/pack/ && + csha1=$(git rev-parse HEAD^{commit}) && + git reset --hard HEAD^ && + sleep 1 && + git reflog expire --expire=now --expire-unreachable=now --all && + # The pack-objects call on the next line is equivalent to + # git repack -A -d without the call to prune-packed + git pack-objects --honor-pack-keep --non-empty --all --reflog \ + --unpack-unreachable .git/objects/info/alternates && + test_must_fail git show $csha1 + ' + + test_expect_success 'local packed unreachable obs that exist in alternate ODB are not loosened' ' + echo `pwd`/alt_objects > .git/objects/info/alternates && + echo "$csha1" | git pack-objects --non-empty --all --reflog pack && + rm -f .git/objects/pack/* && + mv pack-* .git/objects/pack/ && + # The pack-objects call on the next line is equivalent to + # git repack -A -d without the call to prune-packed + git pack-objects --honor-pack-keep --non-empty --all --reflog \ + --unpack-unreachable .git/objects/info/alternates && + test_must_fail git show $csha1 + ' + test_done