From: Junio C Hamano Date: Sun, 22 Apr 2007 00:21:10 +0000 (-0700) Subject: Merge branch 'lt/gitlink' X-Git-Tag: v1.5.2-rc0~19 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/afb5b6a24bd333d298d10acac731f1c127bbb82d?ds=inline;hp=-c Merge branch 'lt/gitlink' * lt/gitlink: Tests for core subproject support Expose subprojects as special files to "git diff" machinery Fix some "git ls-files -o" fallout from gitlinks Teach "git-read-tree -u" to check out submodules as a directory Teach git list-objects logic to not follow gitlinks Fix gitlink index entry filesystem matching Teach "git-read-tree -u" to check out submodules as a directory Teach git list-objects logic not to follow gitlinks Don't show gitlink directories when we want "other" files Teach git-update-index about gitlinks Teach directory traversal about subprojects Fix thinko in subproject entry sorting Teach core object handling functions about gitlinks Teach "fsck" not to follow subproject links Add "S_IFDIRLNK" file mode infrastructure for git links Add 'resolve_gitlink_ref()' helper function Avoid overflowing name buffer in deep directory structures diff-lib: use ce_mode_from_stat() rather than messing with modes manually --- afb5b6a24bd333d298d10acac731f1c127bbb82d diff --combined builtin-fsck.c index f480e700e9,f22de8deaa..fcb8ed5af1 --- a/builtin-fsck.c +++ b/builtin-fsck.c @@@ -253,6 -253,7 +253,7 @@@ static int fsck_tree(struct tree *item case S_IFREG | 0644: case S_IFLNK: case S_IFDIR: + case S_IFDIRLNK: break; /* * This is nonstandard, but we had a few of these @@@ -534,7 -535,7 +535,7 @@@ static void get_default_heads(void * "show_unreachable" flag. */ if (!default_refs) { - error("No default references"); + fprintf(stderr, "notice: No default references\n"); show_unreachable = 0; } } @@@ -554,23 -555,15 +555,23 @@@ static int fsck_head_link(void { unsigned char sha1[20]; int flag; - const char *head_points_at = resolve_ref("HEAD", sha1, 1, &flag); - - if (!head_points_at || !(flag & REF_ISSYMREF)) - return error("HEAD is not a symbolic ref"); - if (prefixcmp(head_points_at, "refs/heads/")) + int null_is_error = 0; + const char *head_points_at = resolve_ref("HEAD", sha1, 0, &flag); + + if (!head_points_at) + return error("Invalid HEAD"); + if (!strcmp(head_points_at, "HEAD")) + /* detached HEAD */ + null_is_error = 1; + else if (prefixcmp(head_points_at, "refs/heads/")) return error("HEAD points to something strange (%s)", head_points_at); - if (is_null_sha1(sha1)) - return error("HEAD: not a valid git pointer"); + if (is_null_sha1(sha1)) { + if (null_is_error) + return error("HEAD: detached HEAD points at nothing"); + fprintf(stderr, "notice: HEAD points to an unborn branch (%s)\n", + head_points_at + 11); + } return 0; } @@@ -661,7 -654,7 +662,7 @@@ int cmd_fsck(int argc, char **argv, con verify_pack(p, 0); for (p = packed_git; p; p = p->next) { - uint32_t i, num = num_packed_objects(p); + uint32_t i, num = p->num_objects; for (i = 0; i < num; i++) fsck_sha1(nth_packed_object_sha1(p, i)); } @@@ -703,8 -696,14 +704,14 @@@ int i; read_cache(); for (i = 0; i < active_nr; i++) { - struct blob *blob = lookup_blob(active_cache[i]->sha1); + unsigned int mode; + struct blob *blob; struct object *obj; + + mode = ntohl(active_cache[i]->ce_mode); + if (S_ISDIRLNK(mode)) + continue; + blob = lookup_blob(active_cache[i]->sha1); if (!blob) continue; obj = &blob->object; diff --combined builtin-update-index.c index e5541df284,c4eaa94998..8f9899178b --- a/builtin-update-index.c +++ b/builtin-update-index.c @@@ -9,6 -9,7 +9,7 @@@ #include "cache-tree.h" #include "tree-walk.h" #include "builtin.h" + #include "refs.h" /* * Default to not allowing changes to the list of files. The @@@ -60,78 -61,153 +61,153 @@@ static int mark_valid(const char *path return -1; } - static int process_file(const char *path) + static int remove_one_path(const char *path) { - int size, namelen, option, status; - struct cache_entry *ce; - struct stat st; - - status = lstat(path, &st); + if (!allow_remove) + return error("%s: does not exist and --remove not passed", path); + if (remove_file_from_cache(path)) + return error("%s: cannot remove from the index", path); + return 0; + } - /* We probably want to do this in remove_file_from_cache() and - * add_cache_entry() instead... - */ - cache_tree_invalidate_path(active_cache_tree, path); + /* + * Handle a path that couldn't be lstat'ed. It's either: + * - missing file (ENOENT or ENOTDIR). That's ok if we're + * supposed to be removing it and the removal actually + * succeeds. + * - permission error. That's never ok. + */ + static int process_lstat_error(const char *path, int err) + { + if (err == ENOENT || err == ENOTDIR) + return remove_one_path(path); + return error("lstat(\"%s\"): %s", path, strerror(errno)); + } - if (status < 0 || S_ISDIR(st.st_mode)) { - /* When we used to have "path" and now we want to add - * "path/file", we need a way to remove "path" before - * being able to add "path/file". However, - * "git-update-index --remove path" would not work. - * --force-remove can be used but this is more user - * friendly, especially since we can do the opposite - * case just fine without --force-remove. - */ - if (status == 0 || (errno == ENOENT || errno == ENOTDIR)) { - if (allow_remove) { - if (remove_file_from_cache(path)) - return error("%s: cannot remove from the index", - path); - else - return 0; - } else if (status < 0) { - return error("%s: does not exist and --remove not passed", - path); - } - } - if (0 == status) - return error("%s: is a directory - add files inside instead", - path); - else - return error("lstat(\"%s\"): %s", path, - strerror(errno)); - } + static int add_one_path(struct cache_entry *old, const char *path, int len, struct stat *st) + { + int option, size = cache_entry_size(len); + struct cache_entry *ce = xcalloc(1, size); - namelen = strlen(path); - size = cache_entry_size(namelen); - ce = xcalloc(1, size); - memcpy(ce->name, path, namelen); - ce->ce_flags = htons(namelen); - fill_stat_cache_info(ce, &st); - - if (trust_executable_bit && has_symlinks) - ce->ce_mode = create_ce_mode(st.st_mode); - else { - /* If there is an existing entry, pick the mode bits and type - * from it, otherwise assume unexecutable regular file. - */ - struct cache_entry *ent; - int pos = cache_name_pos(path, namelen); - - ent = (0 <= pos) ? active_cache[pos] : NULL; - ce->ce_mode = ce_mode_from_stat(ent, st.st_mode); - } + memcpy(ce->name, path, len); + ce->ce_flags = htons(len); + fill_stat_cache_info(ce, st); + ce->ce_mode = ce_mode_from_stat(old, st->st_mode); - if (index_path(ce->sha1, path, &st, !info_only)) + if (index_path(ce->sha1, path, st, !info_only)) return -1; option = allow_add ? ADD_CACHE_OK_TO_ADD : 0; option |= allow_replace ? ADD_CACHE_OK_TO_REPLACE : 0; if (add_cache_entry(ce, option)) - return error("%s: cannot add to the index - missing --add option?", - path); + return error("%s: cannot add to the index - missing --add option?", path); return 0; } + /* + * Handle a path that was a directory. Four cases: + * + * - it's already a gitlink in the index, and we keep it that + * way, and update it if we can (if we cannot find the HEAD, + * we're going to keep it unchanged in the index!) + * + * - it's a *file* in the index, in which case it should be + * removed as a file if removal is allowed, since it doesn't + * exist as such any more. If removal isn't allowed, it's + * an error. + * + * (NOTE! This is old and arguably fairly strange behaviour. + * We might want to make this an error unconditionally, and + * use "--force-remove" if you actually want to force removal). + * + * - it used to exist as a subdirectory (ie multiple files with + * this particular prefix) in the index, in which case it's wrong + * to try to update it as a directory. + * + * - it doesn't exist at all in the index, but it is a valid + * git directory, and it should be *added* as a gitlink. + */ + static int process_directory(const char *path, int len, struct stat *st) + { + unsigned char sha1[20]; + int pos = cache_name_pos(path, len); + + /* Exact match: file or existing gitlink */ + if (pos >= 0) { + struct cache_entry *ce = active_cache[pos]; + if (S_ISDIRLNK(ntohl(ce->ce_mode))) { + + /* Do nothing to the index if there is no HEAD! */ + if (resolve_gitlink_ref(path, "HEAD", sha1) < 0) + return 0; + + return add_one_path(ce, path, len, st); + } + /* Should this be an unconditional error? */ + return remove_one_path(path); + } + + /* Inexact match: is there perhaps a subdirectory match? */ + pos = -pos-1; + while (pos < active_nr) { + struct cache_entry *ce = active_cache[pos++]; + + if (strncmp(ce->name, path, len)) + break; + if (ce->name[len] > '/') + break; + if (ce->name[len] < '/') + continue; + + /* Subdirectory match - error out */ + return error("%s: is a directory - add individual files instead", path); + } + + /* No match - should we add it as a gitlink? */ + if (!resolve_gitlink_ref(path, "HEAD", sha1)) + return add_one_path(NULL, path, len, st); + + /* Error out. */ + return error("%s: is a directory - add files inside instead", path); + } + + /* + * Process a regular file + */ + static int process_file(const char *path, int len, struct stat *st) + { + int pos = cache_name_pos(path, len); + struct cache_entry *ce = pos < 0 ? NULL : active_cache[pos]; + + if (ce && S_ISDIRLNK(ntohl(ce->ce_mode))) + return error("%s is already a gitlink, not replacing", path); + + return add_one_path(ce, path, len, st); + } + + static int process_path(const char *path) + { + int len; + struct stat st; + + /* We probably want to do this in remove_file_from_cache() and + * add_cache_entry() instead... + */ + cache_tree_invalidate_path(active_cache_tree, path); + + /* + * First things first: get the stat information, to decide + * what to do about the pathname! + */ + if (lstat(path, &st) < 0) + return process_lstat_error(path, errno); + + len = strlen(path); + if (S_ISDIR(st.st_mode)) + return process_directory(path, len, &st); + + return process_file(path, len, &st); + } + static int add_cacheinfo(unsigned int mode, const unsigned char *sha1, const char *path, int stage) { @@@ -210,8 -286,8 +286,8 @@@ static void update_one(const char *path report("remove '%s'", path); goto free_return; } - if (process_file(p)) - die("Unable to process file %s", path); + if (process_path(p)) + die("Unable to process path %s", path); report("add '%s'", path); free_return: if (p < path || p > path + strlen(path)) @@@ -227,7 -303,6 +303,7 @@@ static void read_index_info(int line_te char *path_name; unsigned char sha1[20]; unsigned int mode; + unsigned long ul; int stage; /* This reads lines formatted in one of three formats: @@@ -250,12 -325,9 +326,12 @@@ if (buf.eof) break; - mode = strtoul(buf.buf, &ptr, 8); - if (ptr == buf.buf || *ptr != ' ') + errno = 0; + ul = strtoul(buf.buf, &ptr, 8); + if (ptr == buf.buf || *ptr != ' ' + || errno || (unsigned int) ul != ul) goto bad_line; + mode = ul; tab = strchr(ptr, '\t'); if (!tab || tab - ptr < 41) @@@ -551,7 -623,7 +627,7 @@@ int cmd_update_index(int argc, const ch if (i+3 >= argc) die("git-update-index: --cacheinfo "); - if ((sscanf(argv[i+1], "%o", &mode) != 1) || + if (strtoul_ui(argv[i+1], 8, &mode) || get_sha1_hex(argv[i+2], sha1) || add_cacheinfo(mode, sha1, argv[i+3], 0)) die("git-update-index: --cacheinfo" diff --combined cache.h index ead119609a,1b3d00ee11..8747d01c60 --- a/cache.h +++ b/cache.h @@@ -24,6 -24,22 +24,22 @@@ #define DTYPE(de) DT_UNKNOWN #endif + /* + * A "directory link" is a link to another git directory. + * + * The value 0160000 is not normally a valid mode, and + * also just happens to be S_IFDIR + S_IFLNK + * + * NOTE! We *really* shouldn't depend on the S_IFxxx macros + * always having the same values everywhere. We should use + * our internal git values for these things, and then we can + * translate that to the OS-specific value. It just so + * happens that everybody shares the same bit representation + * in the UNIX world (and apparently wider too..) + */ + #define S_IFDIRLNK 0160000 + #define S_ISDIRLNK(m) (((m) & S_IFMT) == S_IFDIRLNK) + /* * Intensive research over the course of many years has shown that * port 9418 is totally unused by anything else. Or @@@ -104,6 -120,8 +120,8 @@@ static inline unsigned int create_ce_mo { if (S_ISLNK(mode)) return htonl(S_IFLNK); + if (S_ISDIR(mode) || S_ISDIRLNK(mode)) + return htonl(S_IFDIRLNK); return htonl(S_IFREG | ce_permissions(mode)); } static inline unsigned int ce_mode_from_stat(struct cache_entry *ce, unsigned int mode) @@@ -121,7 -139,7 +139,7 @@@ } #define canon_mode(mode) \ (S_ISREG(mode) ? (S_IFREG | ce_permissions(mode)) : \ - S_ISLNK(mode) ? S_IFLNK : S_IFDIR) + S_ISLNK(mode) ? S_IFLNK : S_ISDIR(mode) ? S_IFDIR : S_IFDIRLNK) #define cache_entry_size(len) ((offsetof(struct cache_entry,name) + (len) + 8) & ~7) @@@ -217,7 -235,7 +235,7 @@@ extern int commit_locked_index(struct l extern void set_alternate_index_output(const char *); extern void rollback_lock_file(struct lock_file *); -extern int delete_ref(const char *, unsigned char *sha1); +extern int delete_ref(const char *, const unsigned char *sha1); /* Environment bits from configuration mechanism */ extern int use_legacy_headers; @@@ -376,12 -394,11 +394,12 @@@ struct pack_window extern struct packed_git { struct packed_git *next; struct pack_window *windows; - const void *index_data; - off_t index_size; off_t pack_size; - time_t mtime; + const void *index_data; + size_t index_size; + uint32_t num_objects; int index_version; + time_t mtime; int pack_fd; int pack_local; unsigned char sha1[20]; @@@ -432,11 -449,11 +450,11 @@@ extern void pack_report(void) extern unsigned char* use_pack(struct packed_git *, struct pack_window **, off_t, unsigned int *); extern void unuse_pack(struct pack_window **); extern struct packed_git *add_packed_git(const char *, int, int); -extern uint32_t num_packed_objects(const struct packed_git *p); extern const unsigned char *nth_packed_object_sha1(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 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 *); /* Dumb servers support */ @@@ -473,8 -490,8 +491,8 @@@ extern int pager_in_use extern int pager_use_color; /* base85 */ -int decode_85(char *dst, char *line, int linelen); -void encode_85(char *buf, unsigned char *data, int bytes); +int decode_85(char *dst, const char *line, int linelen); +void encode_85(char *buf, const unsigned char *data, int bytes); /* alloc.c */ struct blob; diff --combined diff-lib.c index 7531e20c78,c6d127346a..07f4e8106a --- a/diff-lib.c +++ b/diff-lib.c @@@ -142,34 -142,18 +142,34 @@@ static int queue_diff(struct diff_optio } } +/* + * Does the path name a blob in the working tree, or a directory + * in the working tree? + */ static int is_in_index(const char *path) { - int len = strlen(path); - int pos = cache_name_pos(path, len); - char c; - - if (pos < 0) - return 0; - if (strncmp(active_cache[pos]->name, path, len)) - return 0; - c = active_cache[pos]->name[len]; - return c == '\0' || c == '/'; + int len, pos; + struct cache_entry *ce; + + len = strlen(path); + while (path[len-1] == '/') + len--; + if (!len) + return 1; /* "." */ + pos = cache_name_pos(path, len); + if (0 <= pos) + return 1; + pos = -1 - pos; + while (pos < active_nr) { + ce = active_cache[pos++]; + if (ce_namelen(ce) <= len || + strncmp(ce->name, path, len) || + (ce->name[len] > '/')) + break; /* path cannot be a prefix */ + if (ce->name[len] == '/') + return 1; + } + return 0; } static int handle_diff_files_args(struct rev_info *revs, @@@ -373,7 -357,7 +373,7 @@@ int run_diff_files(struct rev_info *rev continue; } else - dpath->mode = canon_mode(st.st_mode); + dpath->mode = ntohl(ce_mode_from_stat(ce, st.st_mode)); while (i < entries) { struct cache_entry *nce = active_cache[i]; @@@ -390,8 -374,7 +390,7 @@@ int mode = ntohl(nce->ce_mode); num_compare_stages++; hashcpy(dpath->parent[stage-2].sha1, nce->sha1); - dpath->parent[stage-2].mode = - canon_mode(mode); + dpath->parent[stage-2].mode = ntohl(ce_mode_from_stat(nce, mode)); dpath->parent[stage-2].status = DIFF_STATUS_MODIFIED; } @@@ -440,15 -423,7 +439,7 @@@ if (!changed && !revs->diffopt.find_copies_harder) continue; oldmode = ntohl(ce->ce_mode); - - newmode = canon_mode(st.st_mode); - if (!trust_executable_bit && - S_ISREG(newmode) && S_ISREG(oldmode) && - ((newmode ^ oldmode) == 0111)) - newmode = oldmode; - else if (!has_symlinks && - S_ISREG(newmode) && S_ISLNK(oldmode)) - newmode = oldmode; + newmode = ntohl(ce_mode_from_stat(ce, st.st_mode)); diff_change(&revs->diffopt, oldmode, newmode, ce->sha1, (changed ? null_sha1 : ce->sha1), ce->name, NULL); diff --combined refs.c index f9b8802003,11a67a8c86..89876bff87 --- a/refs.c +++ b/refs.c @@@ -47,7 -47,22 +47,7 @@@ static struct ref_list *add_ref(const c struct ref_list **new_entry) { int len; - struct ref_list **p = &list, *entry; - - /* Find the place to insert the ref into.. */ - while ((entry = *p) != NULL) { - int cmp = strcmp(entry->name, name); - if (cmp > 0) - break; - - /* Same as existing entry? */ - if (!cmp) { - if (new_entry) - *new_entry = entry; - return list; - } - p = &entry->next; - } + struct ref_list *entry; /* Allocate it and add it in.. */ len = strlen(name) + 1; @@@ -56,94 -71,11 +56,94 @@@ hashclr(entry->peeled); memcpy(entry->name, name, len); entry->flag = flag; - entry->next = *p; - *p = entry; + entry->next = list; if (new_entry) *new_entry = entry; - return list; + return entry; +} + +/* merge sort the ref list */ +static struct ref_list *sort_ref_list(struct ref_list *list) +{ + int psize, qsize, last_merge_count, cmp; + struct ref_list *p, *q, *l, *e; + struct ref_list *new_list = list; + int k = 1; + int merge_count = 0; + + if (!list) + return list; + + do { + last_merge_count = merge_count; + merge_count = 0; + + psize = 0; + + p = new_list; + q = new_list; + new_list = NULL; + l = NULL; + + while (p) { + merge_count++; + + while (psize < k && q->next) { + q = q->next; + psize++; + } + qsize = k; + + while ((psize > 0) || (qsize > 0 && q)) { + if (qsize == 0 || !q) { + e = p; + p = p->next; + psize--; + } else if (psize == 0) { + e = q; + q = q->next; + qsize--; + } else { + cmp = strcmp(q->name, p->name); + if (cmp < 0) { + e = q; + q = q->next; + qsize--; + } else if (cmp > 0) { + e = p; + p = p->next; + psize--; + } else { + if (hashcmp(q->sha1, p->sha1)) + die("Duplicated ref, and SHA1s don't match: %s", + q->name); + warning("Duplicated ref: %s", q->name); + e = q; + q = q->next; + qsize--; + free(e); + e = p; + p = p->next; + psize--; + } + } + + e->next = NULL; + + if (l) + l->next = e; + if (!new_list) + new_list = e; + l = e; + } + + p = q; + }; + + k = k * 2; + } while ((last_merge_count != merge_count) || (last_merge_count != 1)); + + return new_list; } /* @@@ -210,7 -142,7 +210,7 @@@ static void read_packed_refs(FILE *f, s !get_sha1_hex(refline + 1, sha1)) hashcpy(last->peeled, sha1); } - cached_refs->packed = list; + cached_refs->packed = sort_ref_list(list); } static struct ref_list *get_packed_refs(void) @@@ -269,7 -201,7 +269,7 @@@ static struct ref_list *get_ref_dir(con free(ref); closedir(dir); } - return list; + return sort_ref_list(list); } static struct ref_list *get_loose_refs(void) @@@ -283,6 -215,86 +283,86 @@@ /* We allow "recursive" symbolic refs. Only within reason, though */ #define MAXDEPTH 5 + #define MAXREFLEN (1024) + + static int resolve_gitlink_packed_ref(char *name, int pathlen, const char *refname, unsigned char *result) + { + FILE *f; + struct cached_refs refs; + struct ref_list *ref; + int retval; + + strcpy(name + pathlen, "packed-refs"); + f = fopen(name, "r"); + if (!f) + return -1; + read_packed_refs(f, &refs); + fclose(f); + ref = refs.packed; + retval = -1; + while (ref) { + if (!strcmp(ref->name, refname)) { + retval = 0; + memcpy(result, ref->sha1, 20); + break; + } + ref = ref->next; + } + free_ref_list(refs.packed); + return retval; + } + + static int resolve_gitlink_ref_recursive(char *name, int pathlen, const char *refname, unsigned char *result, int recursion) + { + int fd, len = strlen(refname); + char buffer[128], *p; + + if (recursion > MAXDEPTH || len > MAXREFLEN) + return -1; + memcpy(name + pathlen, refname, len+1); + fd = open(name, O_RDONLY); + if (fd < 0) + return resolve_gitlink_packed_ref(name, pathlen, refname, result); + + len = read(fd, buffer, sizeof(buffer)-1); + close(fd); + if (len < 0) + return -1; + while (len && isspace(buffer[len-1])) + len--; + buffer[len] = 0; + + /* Was it a detached head or an old-fashioned symlink? */ + if (!get_sha1_hex(buffer, result)) + return 0; + + /* Symref? */ + if (strncmp(buffer, "ref:", 4)) + return -1; + p = buffer + 4; + while (isspace(*p)) + p++; + + return resolve_gitlink_ref_recursive(name, pathlen, p, result, recursion+1); + } + + int resolve_gitlink_ref(const char *path, const char *refname, unsigned char *result) + { + int len = strlen(path), retval; + char *gitdir; + + while (len && path[len-1] == '/') + len--; + if (!len) + return -1; + gitdir = xmalloc(len + MAXREFLEN + 8); + memcpy(gitdir, path, len); + memcpy(gitdir + len, "/.git/", 7); + + retval = resolve_gitlink_ref_recursive(gitdir, len+6, refname, result, 0); + free(gitdir); + return retval; + } const char *resolve_ref(const char *ref, unsigned char *sha1, int reading, int *flag) { @@@ -773,7 -785,7 +853,7 @@@ static int repack_without_ref(const cha return commit_lock_file(&packlock); } -int delete_ref(const char *refname, unsigned char *sha1) +int delete_ref(const char *refname, const unsigned char *sha1) { struct ref_lock *lock; int err, i, ret = 0, flag = 0; diff --combined sha1_file.c index 5dac4666b6,ab915faa6b..0c0fcc597d --- a/sha1_file.c +++ b/sha1_file.c @@@ -13,6 -13,7 +13,7 @@@ #include "commit.h" #include "tag.h" #include "tree.h" + #include "refs.h" #ifndef O_NOATIME #if defined(__linux__) && (defined(__i386__) || defined(__PPC__)) @@@ -437,7 -438,7 +438,7 @@@ static int check_packed_git_idx(const c void *idx_map; struct pack_idx_header *hdr; size_t idx_size; - uint32_t nr, i, *index; + uint32_t version, nr, i, *index; int fd = open(path, O_RDONLY); struct stat st; @@@ -455,23 -456,21 +456,23 @@@ idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0); close(fd); - /* a future index format would start with this, as older git - * binaries would fail the non-monotonic index check below. - * give a nicer warning to the user if we can. - */ hdr = idx_map; if (hdr->idx_signature == htonl(PACK_IDX_SIGNATURE)) { - munmap(idx_map, idx_size); - return error("index file %s is a newer version" - " and is not supported by this binary" - " (try upgrading GIT to a newer version)", - path); - } + version = ntohl(hdr->idx_version); + if (version < 2 || version > 2) { + munmap(idx_map, idx_size); + return error("index file %s is version %d" + " and is not supported by this binary" + " (try upgrading GIT to a newer version)", + path, version); + } + } else + version = 1; nr = 0; index = idx_map; + if (version > 1) + index += 2; /* skip index header */ for (i = 0; i < 256; i++) { uint32_t n = ntohl(index[i]); if (n < nr) { @@@ -481,51 -480,21 +482,51 @@@ nr = n; } - /* - * Total size: - * - 256 index entries 4 bytes each - * - 24-byte entries * nr (20-byte sha1 + 4-byte offset) - * - 20-byte SHA1 of the packfile - * - 20-byte SHA1 file checksum - */ - if (idx_size != 4*256 + nr * 24 + 20 + 20) { - munmap(idx_map, idx_size); - return error("wrong index file size in %s", path); + if (version == 1) { + /* + * Total size: + * - 256 index entries 4 bytes each + * - 24-byte entries * nr (20-byte sha1 + 4-byte offset) + * - 20-byte SHA1 of the packfile + * - 20-byte SHA1 file checksum + */ + if (idx_size != 4*256 + nr * 24 + 20 + 20) { + munmap(idx_map, idx_size); + return error("wrong index file size in %s", path); + } + } else if (version == 2) { + /* + * Minimum size: + * - 8 bytes of header + * - 256 index entries 4 bytes each + * - 20-byte sha1 entry * nr + * - 4-byte crc entry * nr + * - 4-byte offset entry * nr + * - 20-byte SHA1 of the packfile + * - 20-byte SHA1 file checksum + * And after the 4-byte offset table might be a + * variable sized table containing 8-byte entries + * for offsets larger than 2^31. + */ + unsigned long min_size = 8 + 4*256 + nr*(20 + 4 + 4) + 20 + 20; + if (idx_size < min_size || idx_size > min_size + (nr - 1)*8) { + munmap(idx_map, idx_size); + return error("wrong index file size in %s", path); + } + if (idx_size != min_size) { + /* make sure we can deal with large pack offsets */ + off_t x = 0x7fffffffUL, y = 0xffffffffUL; + if (x > (x + 1) || y > (y + 1)) { + munmap(idx_map, idx_size); + return error("pack too large for current definition of off_t in %s", path); + } + } } - p->index_version = 1; + p->index_version = version; p->index_data = idx_map; p->index_size = idx_size; + p->num_objects = nr; return 0; } @@@ -637,11 -606,11 +638,11 @@@ static int open_packed_git_1(struct pac p->pack_name, ntohl(hdr.hdr_version)); /* Verify the pack matches its index. */ - if (num_packed_objects(p) != ntohl(hdr.hdr_entries)) + if (p->num_objects != ntohl(hdr.hdr_entries)) return error("packfile %s claims to have %u objects" - " while index size indicates %u objects", - p->pack_name, ntohl(hdr.hdr_entries), - num_packed_objects(p)); + " while index indicates %u objects", + p->pack_name, ntohl(hdr.hdr_entries), + p->num_objects); if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1) return error("end of packfile %s is unavailable", p->pack_name); if (read_in_full(p->pack_fd, sha1, sizeof(sha1)) != sizeof(sha1)) @@@ -1160,43 -1129,6 +1161,43 @@@ static void *unpack_sha1_file(void *map return unpack_sha1_rest(&stream, hdr, *size, sha1); } +unsigned long get_size_from_delta(struct packed_git *p, + struct pack_window **w_curs, + off_t curpos) +{ + const unsigned char *data; + unsigned char delta_head[20], *in; + z_stream stream; + int st; + + memset(&stream, 0, sizeof(stream)); + stream.next_out = delta_head; + stream.avail_out = sizeof(delta_head); + + inflateInit(&stream); + do { + in = use_pack(p, w_curs, curpos, &stream.avail_in); + stream.next_in = in; + st = inflate(&stream, Z_FINISH); + curpos += stream.next_in - in; + } while ((st == Z_OK || st == Z_BUF_ERROR) && + stream.total_out < sizeof(delta_head)); + inflateEnd(&stream); + if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) + die("delta data unpack-initial failed"); + + /* Examine the initial part of the delta to figure out + * the result size. + */ + data = delta_head; + + /* ignore base size */ + get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); + + /* Read the result size */ + return get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); +} + static off_t get_delta_base(struct packed_git *p, struct pack_window **w_curs, off_t *curpos, @@@ -1218,7 -1150,7 +1219,7 @@@ base_offset = c & 127; while (c & 128) { base_offset += 1; - if (!base_offset || base_offset & ~(~0UL >> 7)) + if (!base_offset || MSB(base_offset, 7)) die("offset value overflow for delta base object"); c = base_info[used++]; base_offset = (base_offset << 7) + (c & 127); @@@ -1260,8 -1192,40 +1261,8 @@@ static int packed_delta_info(struct pac * based on a base with a wrong size. This saves tons of * inflate() calls. */ - if (sizep) { - const unsigned char *data; - unsigned char delta_head[20], *in; - z_stream stream; - int st; - - memset(&stream, 0, sizeof(stream)); - stream.next_out = delta_head; - stream.avail_out = sizeof(delta_head); - - inflateInit(&stream); - do { - in = use_pack(p, w_curs, curpos, &stream.avail_in); - stream.next_in = in; - st = inflate(&stream, Z_FINISH); - curpos += stream.next_in - in; - } while ((st == Z_OK || st == Z_BUF_ERROR) - && stream.total_out < sizeof(delta_head)); - inflateEnd(&stream); - if ((st != Z_STREAM_END) && - stream.total_out != sizeof(delta_head)) - die("delta data unpack-initial failed"); - - /* Examine the initial part of the delta to figure out - * the result size. - */ - data = delta_head; - - /* ignore base size */ - get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); - - /* Read the result size */ - *sizep = get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); - } + if (sizep) + *sizep = get_size_from_delta(p, w_curs, curpos); return type; } @@@ -1563,60 -1527,37 +1564,60 @@@ void *unpack_entry(struct packed_git *p return data; } -uint32_t num_packed_objects(const struct packed_git *p) +const unsigned char *nth_packed_object_sha1(const struct packed_git *p, + uint32_t n) { - /* See check_packed_git_idx() */ - return (uint32_t)((p->index_size - 20 - 20 - 4*256) / 24); + const unsigned char *index = p->index_data; + if (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 unsigned char *nth_packed_object_sha1(const struct packed_git *p, - uint32_t n) +static off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n) { const unsigned char *index = p->index_data; index += 4 * 256; - if (num_packed_objects(p) <= n) - return NULL; - return index + 24 * n + 4; + if (p->index_version == 1) { + return ntohl(*((uint32_t *)(index + 24 * n))); + } else { + uint32_t off; + index += 8 + p->num_objects * (20 + 4); + off = ntohl(*((uint32_t *)(index + 4 * n))); + if (!(off & 0x80000000)) + return off; + index += p->num_objects * 4 + (off & 0x7fffffff) * 8; + return (((uint64_t)ntohl(*((uint32_t *)(index + 0)))) << 32) | + ntohl(*((uint32_t *)(index + 4))); + } } off_t find_pack_entry_one(const unsigned char *sha1, struct packed_git *p) { const uint32_t *level1_ofs = p->index_data; - int hi = ntohl(level1_ofs[*sha1]); - int lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1])); const unsigned char *index = p->index_data; + unsigned hi, lo; + if (p->index_version > 1) { + level1_ofs += 2; + index += 8; + } index += 4 * 256; + hi = ntohl(level1_ofs[*sha1]); + lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1])); do { - int mi = (lo + hi) / 2; - int cmp = hashcmp(index + 24 * mi + 4, sha1); + unsigned mi = (lo + hi) / 2; + unsigned x = (p->index_version > 1) ? (mi * 20) : (mi * 24 + 4); + int cmp = hashcmp(index + x, sha1); if (!cmp) - return ntohl(*((uint32_t *)((char *)index + (24 * mi)))); + return nth_packed_object_offset(p, mi); if (cmp > 0) hi = mi; else @@@ -2392,6 -2333,8 +2393,8 @@@ int index_path(unsigned char *sha1, con path); free(target); break; + case S_IFDIR: + return resolve_gitlink_ref(path, "HEAD", sha1); default: return error("%s: unsupported file type", path); }