diff options
Diffstat (limited to 'sha1_file.c')
| -rw-r--r-- | sha1_file.c | 854 |
1 files changed, 575 insertions, 279 deletions
diff --git a/sha1_file.c b/sha1_file.c index cb571ac6e8..ec957db5e1 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -23,20 +23,22 @@ #include "bulk-checkin.h" #include "streaming.h" #include "dir.h" - -#ifndef O_NOATIME -#if defined(__linux__) && (defined(__i386__) || defined(__PPC__)) -#define O_NOATIME 01000000 -#else -#define O_NOATIME 0 -#endif -#endif +#include "mru.h" +#include "list.h" +#include "mergesort.h" +#include "quote.h" #define SZ_FMT PRIuMAX static inline uintmax_t sz_fmt(size_t s) { return s; } const unsigned char null_sha1[20]; const struct object_id null_oid; +const struct object_id empty_tree_oid = { + EMPTY_TREE_SHA1_BIN_LITERAL +}; +const struct object_id empty_blob_oid = { + EMPTY_BLOB_SHA1_BIN_LITERAL +}; /* * This is meant to hold a *small* number of objects that you would @@ -59,14 +61,6 @@ static struct cached_object empty_tree = { 0 }; -/* - * A pointer to the last packed_git in which an object was found. - * When an object is sought, we look in this packfile first, because - * objects that are looked up at similar times are often in the same - * packfile as one another. - */ -static struct packed_git *last_found_pack; - static struct cached_object *find_cached_object(const unsigned char *sha1) { int i; @@ -171,36 +165,42 @@ enum scld_error safe_create_leading_directories_const(const char *path) return result; } -static void fill_sha1_path(char *pathbuf, const unsigned char *sha1) +static void fill_sha1_path(struct strbuf *buf, const unsigned char *sha1) { int i; for (i = 0; i < 20; i++) { static char hex[] = "0123456789abcdef"; unsigned int val = sha1[i]; - char *pos = pathbuf + i*2 + (i > 0); - *pos++ = hex[val >> 4]; - *pos = hex[val & 0xf]; + strbuf_addch(buf, hex[val >> 4]); + strbuf_addch(buf, hex[val & 0xf]); + if (!i) + strbuf_addch(buf, '/'); } } const char *sha1_file_name(const unsigned char *sha1) { - static char buf[PATH_MAX]; - const char *objdir; - int len; + static struct strbuf buf = STRBUF_INIT; + + strbuf_reset(&buf); + strbuf_addf(&buf, "%s/", get_object_directory()); + + fill_sha1_path(&buf, sha1); + return buf.buf; +} - objdir = get_object_directory(); - len = strlen(objdir); +struct strbuf *alt_scratch_buf(struct alternate_object_database *alt) +{ + strbuf_setlen(&alt->scratch, alt->base_len); + return &alt->scratch; +} - /* '/' + sha1(2) + '/' + sha1(38) + '\0' */ - if (len + 43 > PATH_MAX) - die("insanely long object directory %s", objdir); - memcpy(buf, objdir, len); - buf[len] = '/'; - buf[len+3] = '/'; - buf[len+42] = '\0'; - fill_sha1_path(buf + len + 1, sha1); - return buf; +static const char *alt_sha1_path(struct alternate_object_database *alt, + const unsigned char *sha1) +{ + struct strbuf *buf = alt_scratch_buf(alt); + fill_sha1_path(buf, sha1); + return buf->buf; } /* @@ -234,6 +234,35 @@ struct alternate_object_database *alt_odb_list; static struct alternate_object_database **alt_odb_tail; /* + * Return non-zero iff the path is usable as an alternate object database. + */ +static int alt_odb_usable(struct strbuf *path, const char *normalized_objdir) +{ + struct alternate_object_database *alt; + + /* Detect cases where alternate disappeared */ + if (!is_directory(path->buf)) { + error("object directory %s does not exist; " + "check .git/objects/info/alternates.", + path->buf); + return 0; + } + + /* + * Prevent the common mistake of listing the same + * thing twice, or object directory itself. + */ + for (alt = alt_odb_list; alt; alt = alt->next) { + if (!fspathcmp(path->buf, alt->path)) + return 0; + } + if (!fspathcmp(path->buf, normalized_objdir)) + return 0; + + return 1; +} + +/* * Prepare alternate object database registry. * * The variable alt_odb_list points at the list of struct @@ -252,59 +281,34 @@ static int link_alt_odb_entry(const char *entry, const char *relative_base, int depth, const char *normalized_objdir) { struct alternate_object_database *ent; - struct alternate_object_database *alt; - size_t pfxlen, entlen; struct strbuf pathbuf = STRBUF_INIT; if (!is_absolute_path(entry) && relative_base) { - strbuf_addstr(&pathbuf, real_path(relative_base)); + strbuf_realpath(&pathbuf, relative_base, 1); strbuf_addch(&pathbuf, '/'); } strbuf_addstr(&pathbuf, entry); - normalize_path_copy(pathbuf.buf, pathbuf.buf); - - pfxlen = strlen(pathbuf.buf); + if (strbuf_normalize_path(&pathbuf) < 0 && relative_base) { + error("unable to normalize alternate object path: %s", + pathbuf.buf); + strbuf_release(&pathbuf); + return -1; + } /* * The trailing slash after the directory name is given by * this function at the end. Remove duplicates. */ - while (pfxlen && pathbuf.buf[pfxlen-1] == '/') - pfxlen -= 1; + while (pathbuf.len && pathbuf.buf[pathbuf.len - 1] == '/') + strbuf_setlen(&pathbuf, pathbuf.len - 1); - entlen = st_add(pfxlen, 43); /* '/' + 2 hex + '/' + 38 hex + NUL */ - ent = xmalloc(st_add(sizeof(*ent), entlen)); - memcpy(ent->base, pathbuf.buf, pfxlen); - strbuf_release(&pathbuf); - - ent->name = ent->base + pfxlen + 1; - ent->base[pfxlen + 3] = '/'; - ent->base[pfxlen] = ent->base[entlen-1] = 0; - - /* Detect cases where alternate disappeared */ - if (!is_directory(ent->base)) { - error("object directory %s does not exist; " - "check .git/objects/info/alternates.", - ent->base); - free(ent); + if (!alt_odb_usable(&pathbuf, normalized_objdir)) { + strbuf_release(&pathbuf); return -1; } - /* Prevent the common mistake of listing the same - * thing twice, or object directory itself. - */ - for (alt = alt_odb_list; alt; alt = alt->next) { - if (pfxlen == alt->name - alt->base - 1 && - !memcmp(ent->base, alt->base, pfxlen)) { - free(ent); - return -1; - } - } - if (!fspathcmp(ent->base, normalized_objdir)) { - free(ent); - return -1; - } + ent = alloc_alt_odb(pathbuf.buf); /* add the alternate entry */ *alt_odb_tail = ent; @@ -312,20 +316,46 @@ static int link_alt_odb_entry(const char *entry, const char *relative_base, ent->next = NULL; /* recursively add alternates */ - read_info_alternates(ent->base, depth + 1); - - ent->base[pfxlen] = '/'; + read_info_alternates(pathbuf.buf, depth + 1); + strbuf_release(&pathbuf); return 0; } +static const char *parse_alt_odb_entry(const char *string, + int sep, + struct strbuf *out) +{ + const char *end; + + strbuf_reset(out); + + if (*string == '#') { + /* comment; consume up to next separator */ + end = strchrnul(string, sep); + } else if (*string == '"' && !unquote_c_style(out, string, &end)) { + /* + * quoted path; unquote_c_style has copied the + * data for us and set "end". Broken quoting (e.g., + * an entry that doesn't end with a quote) falls + * back to the unquoted case below. + */ + } else { + /* normal, unquoted path */ + end = strchrnul(string, sep); + strbuf_add(out, string, end - string); + } + + if (*end) + end++; + return end; +} + static void link_alt_odb_entries(const char *alt, int len, int sep, const char *relative_base, int depth) { - struct string_list entries = STRING_LIST_INIT_NODUP; - char *alt_copy; - int i; struct strbuf objdirbuf = STRBUF_INIT; + struct strbuf entry = STRBUF_INIT; if (depth > 5) { error("%s: ignoring alternate object stores, nesting too deep.", @@ -334,23 +364,17 @@ static void link_alt_odb_entries(const char *alt, int len, int sep, } strbuf_add_absolute_path(&objdirbuf, get_object_directory()); - normalize_path_copy(objdirbuf.buf, objdirbuf.buf); + if (strbuf_normalize_path(&objdirbuf) < 0) + die("unable to normalize object directory: %s", + objdirbuf.buf); - alt_copy = xmemdupz(alt, len); - string_list_split_in_place(&entries, alt_copy, sep, -1); - for (i = 0; i < entries.nr; i++) { - const char *entry = entries.items[i].string; - if (entry[0] == '\0' || entry[0] == '#') + while (*alt) { + alt = parse_alt_odb_entry(alt, sep, &entry); + if (!entry.len) continue; - if (!is_absolute_path(entry) && depth) { - error("%s: ignoring relative alternate object store %s", - relative_base, entry); - } else { - link_alt_odb_entry(entry, relative_base, depth, objdirbuf.buf); - } + link_alt_odb_entry(entry.buf, relative_base, depth, objdirbuf.buf); } - string_list_clear(&entries, 0); - free(alt_copy); + strbuf_release(&entry); strbuf_release(&objdirbuf); } @@ -363,7 +387,7 @@ void read_info_alternates(const char * relative_base, int depth) int fd; path = xstrfmt("%s/info/alternates", relative_base); - fd = git_open_noatime(path); + fd = git_open(path); free(path); if (fd < 0) return; @@ -380,6 +404,18 @@ void read_info_alternates(const char * relative_base, int depth) munmap(map, mapsz); } +struct alternate_object_database *alloc_alt_odb(const char *dir) +{ + struct alternate_object_database *ent; + + FLEX_ALLOC_STR(ent, path, dir); + strbuf_init(&ent->scratch, 0); + strbuf_addf(&ent->scratch, "%s/", dir); + ent->base_len = ent->scratch.len; + + return ent; +} + void add_to_alternates_file(const char *reference) { struct lock_file *lock = xcalloc(1, sizeof(struct lock_file)); @@ -425,6 +461,93 @@ void add_to_alternates_file(const char *reference) free(alts); } +void add_to_alternates_memory(const char *reference) +{ + /* + * Make sure alternates are initialized, or else our entry may be + * overwritten when they are. + */ + prepare_alt_odb(); + + link_alt_odb_entries(reference, strlen(reference), '\n', NULL, 0); +} + +/* + * Compute the exact path an alternate is at and returns it. In case of + * error NULL is returned and the human readable error is added to `err` + * `path` may be relative and should point to $GITDIR. + * `err` must not be null. + */ +char *compute_alternate_path(const char *path, struct strbuf *err) +{ + char *ref_git = NULL; + const char *repo, *ref_git_s; + int seen_error = 0; + + ref_git_s = real_path_if_valid(path); + if (!ref_git_s) { + seen_error = 1; + strbuf_addf(err, _("path '%s' does not exist"), path); + goto out; + } else + /* + * Beware: read_gitfile(), real_path() and mkpath() + * return static buffer + */ + ref_git = xstrdup(ref_git_s); + + repo = read_gitfile(ref_git); + if (!repo) + repo = read_gitfile(mkpath("%s/.git", ref_git)); + if (repo) { + free(ref_git); + ref_git = xstrdup(repo); + } + + if (!repo && is_directory(mkpath("%s/.git/objects", ref_git))) { + char *ref_git_git = mkpathdup("%s/.git", ref_git); + free(ref_git); + ref_git = ref_git_git; + } else if (!is_directory(mkpath("%s/objects", ref_git))) { + struct strbuf sb = STRBUF_INIT; + seen_error = 1; + if (get_common_dir(&sb, ref_git)) { + strbuf_addf(err, + _("reference repository '%s' as a linked " + "checkout is not supported yet."), + path); + goto out; + } + + strbuf_addf(err, _("reference repository '%s' is not a " + "local repository."), path); + goto out; + } + + if (!access(mkpath("%s/shallow", ref_git), F_OK)) { + strbuf_addf(err, _("reference repository '%s' is shallow"), + path); + seen_error = 1; + goto out; + } + + if (!access(mkpath("%s/info/grafts", ref_git), F_OK)) { + strbuf_addf(err, + _("reference repository '%s' is grafted"), + path); + seen_error = 1; + goto out; + } + +out: + if (seen_error) { + free(ref_git); + ref_git = NULL; + } + + return ref_git; +} + int foreach_alt_odb(alt_odb_fn fn, void *cb) { struct alternate_object_database *ent; @@ -489,8 +612,8 @@ static int check_and_freshen_nonlocal(const unsigned char *sha1, int freshen) struct alternate_object_database *alt; prepare_alt_odb(); for (alt = alt_odb_list; alt; alt = alt->next) { - fill_sha1_path(alt->name, sha1); - if (check_and_freshen_file(alt->base, freshen)) + const char *path = alt_sha1_path(alt, sha1); + if (check_and_freshen_file(path, freshen)) return 1; } return 0; @@ -522,6 +645,9 @@ static size_t peak_pack_mapped; static size_t pack_mapped; struct packed_git *packed_git; +static struct mru packed_git_mru_storage; +struct mru *packed_git_mru = &packed_git_mru_storage; + void pack_report(void) { fprintf(stderr, @@ -554,7 +680,7 @@ static int check_packed_git_idx(const char *path, struct packed_git *p) struct pack_idx_header *hdr; size_t idx_size; uint32_t version, nr, i, *index; - int fd = git_open_noatime(path); + int fd = git_open(path); struct stat st; if (fd < 0) @@ -795,7 +921,7 @@ void close_all_packs(void) for (p = packed_git; p; p = p->next) if (p->do_not_close) - die("BUG! Want to close pack marked 'do-not-close'"); + die("BUG: want to close pack marked 'do-not-close'"); else close_pack(p); } @@ -891,36 +1017,6 @@ void close_pack_index(struct packed_git *p) } } -/* - * This is used by git-repack in case a newly created pack happens to - * contain the same set of objects as an existing one. In that case - * the resulting file might be different even if its name would be the - * same. It is best to close any reference to the old pack before it is - * replaced on disk. Of course no index pointers or windows for given pack - * must subsist at this point. If ever objects from this pack are requested - * again, the new version of the pack will be reinitialized through - * reprepare_packed_git(). - */ -void free_pack_by_name(const char *pack_name) -{ - struct packed_git *p, **pp = &packed_git; - - while (*pp) { - p = *pp; - if (strcmp(pack_name, p->pack_name) == 0) { - clear_delta_base_cache(); - close_pack(p); - free(p->bad_object_sha1); - *pp = p->next; - if (last_found_pack == p) - last_found_pack = NULL; - free(p); - return; - } - pp = &p->next; - } -} - static unsigned int get_max_fd_limit(void) { #ifdef RLIMIT_NOFILE @@ -990,7 +1086,7 @@ static int open_packed_git_1(struct packed_git *p) while (pack_max_fds <= pack_open_fds && close_one_pack()) ; /* nothing */ - p->pack_fd = git_open_noatime(p->pack_name); + p->pack_fd = git_open(p->pack_name); if (p->pack_fd < 0 || fstat(p->pack_fd, &st)) return -1; pack_open_fds++; @@ -1331,10 +1427,46 @@ static void prepare_packed_git_one(char *objdir, int local) strbuf_release(&path); } +static int approximate_object_count_valid; + +/* + * Give a fast, rough count of the number of objects in the repository. This + * ignores loose objects completely. If you have a lot of them, then either + * you should repack because your performance will be awful, or they are + * all unreachable objects about to be pruned, in which case they're not really + * interesting as a measure of repo size in the first place. + */ +unsigned long approximate_object_count(void) +{ + static unsigned long count; + if (!approximate_object_count_valid) { + struct packed_git *p; + + prepare_packed_git(); + count = 0; + for (p = packed_git; p; p = p->next) { + if (open_pack_index(p)) + continue; + count += p->num_objects; + } + } + return count; +} + +static void *get_next_packed_git(const void *p) +{ + return ((const struct packed_git *)p)->next; +} + +static void set_next_packed_git(void *p, void *next) +{ + ((struct packed_git *)p)->next = next; +} + static int sort_pack(const void *a_, const void *b_) { - struct packed_git *a = *((struct packed_git **)a_); - struct packed_git *b = *((struct packed_git **)b_); + const struct packed_git *a = a_; + const struct packed_git *b = b_; int st; /* @@ -1361,28 +1493,17 @@ static int sort_pack(const void *a_, const void *b_) static void rearrange_packed_git(void) { - struct packed_git **ary, *p; - int i, n; - - for (n = 0, p = packed_git; p; p = p->next) - n++; - if (n < 2) - return; - - /* prepare an array of packed_git for easier sorting */ - ary = xcalloc(n, sizeof(struct packed_git *)); - for (n = 0, p = packed_git; p; p = p->next) - ary[n++] = p; - - qsort(ary, n, sizeof(struct packed_git *), sort_pack); + packed_git = llist_mergesort(packed_git, get_next_packed_git, + set_next_packed_git, sort_pack); +} - /* link them back again */ - for (i = 0; i < n - 1; i++) - ary[i]->next = ary[i + 1]; - ary[n - 1]->next = NULL; - packed_git = ary[0]; +static void prepare_packed_git_mru(void) +{ + struct packed_git *p; - free(ary); + mru_clear(packed_git_mru); + for (p = packed_git; p; p = p->next) + mru_append(packed_git_mru, p); } static int prepare_packed_git_run_once = 0; @@ -1394,17 +1515,16 @@ void prepare_packed_git(void) return; prepare_packed_git_one(get_object_directory(), 1); prepare_alt_odb(); - for (alt = alt_odb_list; alt; alt = alt->next) { - alt->name[-1] = 0; - prepare_packed_git_one(alt->base, 0); - alt->name[-1] = '/'; - } + for (alt = alt_odb_list; alt; alt = alt->next) + prepare_packed_git_one(alt->path, 0); rearrange_packed_git(); + prepare_packed_git_mru(); prepare_packed_git_run_once = 1; } void reprepare_packed_git(void) { + approximate_object_count_valid = 0; prepare_packed_git_run_once = 0; prepare_packed_git(); } @@ -1483,61 +1603,81 @@ int check_sha1_signature(const unsigned char *sha1, void *map, return hashcmp(sha1, real_sha1) ? -1 : 0; } -int git_open_noatime(const char *name) +int git_open_cloexec(const char *name, int flags) { - static int sha1_file_open_flag = O_NOATIME; + int fd; + static int o_cloexec = O_CLOEXEC; - for (;;) { - int fd; + fd = open(name, flags | o_cloexec); + if ((o_cloexec & O_CLOEXEC) && fd < 0 && errno == EINVAL) { + /* Try again w/o O_CLOEXEC: the kernel might not support it */ + o_cloexec &= ~O_CLOEXEC; + fd = open(name, flags | o_cloexec); + } - errno = 0; - fd = open(name, O_RDONLY | sha1_file_open_flag); - if (fd >= 0) - return fd; +#if defined(F_GETFL) && defined(F_SETFL) && defined(FD_CLOEXEC) + { + static int fd_cloexec = FD_CLOEXEC; - /* Might the failure be due to O_NOATIME? */ - if (errno != ENOENT && sha1_file_open_flag) { - sha1_file_open_flag = 0; - continue; + if (!o_cloexec && 0 <= fd && fd_cloexec) { + /* Opened w/o O_CLOEXEC? try with fcntl(2) to add it */ + int flags = fcntl(fd, F_GETFL); + if (fcntl(fd, F_SETFL, flags | fd_cloexec)) + fd_cloexec = 0; } - - return -1; } +#endif + return fd; } -static int stat_sha1_file(const unsigned char *sha1, struct stat *st) +/* + * Find "sha1" as a loose object in the local repository or in an alternate. + * Returns 0 on success, negative on failure. + * + * The "path" out-parameter will give the path of the object we found (if any). + * Note that it may point to static storage and is only valid until another + * call to sha1_file_name(), etc. + */ +static int stat_sha1_file(const unsigned char *sha1, struct stat *st, + const char **path) { struct alternate_object_database *alt; - if (!lstat(sha1_file_name(sha1), st)) + *path = sha1_file_name(sha1); + if (!lstat(*path, st)) return 0; prepare_alt_odb(); errno = ENOENT; for (alt = alt_odb_list; alt; alt = alt->next) { - fill_sha1_path(alt->name, sha1); - if (!lstat(alt->base, st)) + *path = alt_sha1_path(alt, sha1); + if (!lstat(*path, st)) return 0; } return -1; } -static int open_sha1_file(const unsigned char *sha1) +/* + * Like stat_sha1_file(), but actually open the object and return the + * descriptor. See the caveats on the "path" parameter above. + */ +static int open_sha1_file(const unsigned char *sha1, const char **path) { int fd; struct alternate_object_database *alt; int most_interesting_errno; - fd = git_open_noatime(sha1_file_name(sha1)); + *path = sha1_file_name(sha1); + fd = git_open(*path); if (fd >= 0) return fd; most_interesting_errno = errno; prepare_alt_odb(); for (alt = alt_odb_list; alt; alt = alt->next) { - fill_sha1_path(alt->name, sha1); - fd = git_open_noatime(alt->base); + *path = alt_sha1_path(alt, sha1); + fd = git_open(*path); if (fd >= 0) return fd; if (most_interesting_errno == ENOENT) @@ -1547,12 +1687,21 @@ static int open_sha1_file(const unsigned char *sha1) return -1; } -void *map_sha1_file(const unsigned char *sha1, unsigned long *size) +/* + * Map the loose object at "path" if it is not NULL, or the path found by + * searching for a loose object named "sha1". + */ +static void *map_sha1_file_1(const char *path, + const unsigned char *sha1, + unsigned long *size) { void *map; int fd; - fd = open_sha1_file(sha1); + if (path) + fd = git_open(path); + else + fd = open_sha1_file(sha1, &path); map = NULL; if (fd >= 0) { struct stat st; @@ -1561,7 +1710,7 @@ void *map_sha1_file(const unsigned char *sha1, unsigned long *size) *size = xsize_t(st.st_size); if (!*size) { /* mmap() is forbidden on empty files */ - error("object file %s is empty", sha1_file_name(sha1)); + error("object file %s is empty", path); return NULL; } map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0); @@ -1571,6 +1720,11 @@ void *map_sha1_file(const unsigned char *sha1, unsigned long *size) return map; } +void *map_sha1_file(const unsigned char *sha1, unsigned long *size) +{ + return map_sha1_file_1(NULL, sha1, size); +} + unsigned long unpack_object_header_buffer(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep) { @@ -1596,7 +1750,9 @@ unsigned long unpack_object_header_buffer(const unsigned char *buf, return used; } -int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz) +static int unpack_sha1_short_header(git_zstream *stream, + unsigned char *map, unsigned long mapsize, + void *buffer, unsigned long bufsiz) { /* Get the data stream */ memset(stream, 0, sizeof(*stream)); @@ -1609,13 +1765,31 @@ int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long ma return git_inflate(stream, 0); } +int unpack_sha1_header(git_zstream *stream, + unsigned char *map, unsigned long mapsize, + void *buffer, unsigned long bufsiz) +{ + int status = unpack_sha1_short_header(stream, map, mapsize, + buffer, bufsiz); + + if (status < Z_OK) + return status; + + /* Make sure we have the terminating NUL */ + if (!memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer)) + return -1; + return 0; +} + static int unpack_sha1_header_to_strbuf(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz, struct strbuf *header) { int status; - status = unpack_sha1_header(stream, map, mapsize, buffer, bufsiz); + status = unpack_sha1_short_header(stream, map, mapsize, buffer, bufsiz); + if (status < Z_OK) + return -1; /* * Check if entire header is unpacked in the first iteration. @@ -1706,6 +1880,8 @@ static int parse_sha1_header_extended(const char *hdr, struct object_info *oi, */ for (;;) { char c = *hdr++; + if (!c) + return -1; if (c == ' ') break; type_len++; @@ -1716,7 +1892,7 @@ static int parse_sha1_header_extended(const char *hdr, struct object_info *oi, strbuf_add(oi->typename, type_buf, type_len); /* * Set type to 0 if its an unknown object and - * we're obtaining the type using '--allow-unkown-type' + * we're obtaining the type using '--allow-unknown-type' * option. */ if ((flags & LOOKUP_UNKNOWN_OBJECT) && (type < 0)) @@ -1754,11 +1930,9 @@ static int parse_sha1_header_extended(const char *hdr, struct object_info *oi, int parse_sha1_header(const char *hdr, unsigned long *sizep) { - struct object_info oi; + struct object_info oi = OBJECT_INFO_INIT; oi.sizep = sizep; - oi.typename = NULL; - oi.typep = NULL; return parse_sha1_header_extended(hdr, &oi, LOOKUP_REPLACE_OBJECT); } @@ -1996,8 +2170,8 @@ unwind: goto out; } -static int packed_object_info(struct packed_git *p, off_t obj_offset, - struct object_info *oi) +int packed_object_info(struct packed_git *p, off_t obj_offset, + struct object_info *oi) { struct pack_window *w_curs = NULL; unsigned long size; @@ -2097,136 +2271,141 @@ static void *unpack_compressed_entry(struct packed_git *p, return buffer; } -#define MAX_DELTA_CACHE (256) - +static struct hashmap delta_base_cache; static size_t delta_base_cached; -static struct delta_base_cache_lru_list { - struct delta_base_cache_lru_list *prev; - struct delta_base_cache_lru_list *next; -} delta_base_cache_lru = { &delta_base_cache_lru, &delta_base_cache_lru }; +static LIST_HEAD(delta_base_cache_lru); -static struct delta_base_cache_entry { - struct delta_base_cache_lru_list lru; - void *data; +struct delta_base_cache_key { struct packed_git *p; off_t base_offset; +}; + +struct delta_base_cache_entry { + struct hashmap hash; + struct delta_base_cache_key key; + struct list_head lru; + void *data; unsigned long size; enum object_type type; -} delta_base_cache[MAX_DELTA_CACHE]; +}; -static unsigned long pack_entry_hash(struct packed_git *p, off_t base_offset) +static unsigned int pack_entry_hash(struct packed_git *p, off_t base_offset) { - unsigned long hash; + unsigned int hash; - hash = (unsigned long)(intptr_t)p + (unsigned long)base_offset; + hash = (unsigned int)(intptr_t)p + (unsigned int)base_offset; hash += (hash >> 8) + (hash >> 16); - return hash % MAX_DELTA_CACHE; + return hash; } static struct delta_base_cache_entry * get_delta_base_cache_entry(struct packed_git *p, off_t base_offset) { - unsigned long hash = pack_entry_hash(p, base_offset); - return delta_base_cache + hash; + struct hashmap_entry entry; + struct delta_base_cache_key key; + + if (!delta_base_cache.cmpfn) + return NULL; + + hashmap_entry_init(&entry, pack_entry_hash(p, base_offset)); + key.p = p; + key.base_offset = base_offset; + return hashmap_get(&delta_base_cache, &entry, &key); } -static int eq_delta_base_cache_entry(struct delta_base_cache_entry *ent, - struct packed_git *p, off_t base_offset) +static int delta_base_cache_key_eq(const struct delta_base_cache_key *a, + const struct delta_base_cache_key *b) { - return (ent->data && ent->p == p && ent->base_offset == base_offset); + return a->p == b->p && a->base_offset == b->base_offset; +} + +static int delta_base_cache_hash_cmp(const void *va, const void *vb, + const void *vkey) +{ + const struct delta_base_cache_entry *a = va, *b = vb; + const struct delta_base_cache_key *key = vkey; + if (key) + return !delta_base_cache_key_eq(&a->key, key); + else + return !delta_base_cache_key_eq(&a->key, &b->key); } static int in_delta_base_cache(struct packed_git *p, off_t base_offset) { - struct delta_base_cache_entry *ent; - ent = get_delta_base_cache_entry(p, base_offset); - return eq_delta_base_cache_entry(ent, p, base_offset); + return !!get_delta_base_cache_entry(p, base_offset); } -static void clear_delta_base_cache_entry(struct delta_base_cache_entry *ent) +/* + * Remove the entry from the cache, but do _not_ free the associated + * entry data. The caller takes ownership of the "data" buffer, and + * should copy out any fields it wants before detaching. + */ +static void detach_delta_base_cache_entry(struct delta_base_cache_entry *ent) { - ent->data = NULL; - ent->lru.next->prev = ent->lru.prev; - ent->lru.prev->next = ent->lru.next; + hashmap_remove(&delta_base_cache, ent, &ent->key); + list_del(&ent->lru); delta_base_cached -= ent->size; + free(ent); } static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset, - unsigned long *base_size, enum object_type *type, int keep_cache) + unsigned long *base_size, enum object_type *type) { struct delta_base_cache_entry *ent; - void *ret; ent = get_delta_base_cache_entry(p, base_offset); - - if (!eq_delta_base_cache_entry(ent, p, base_offset)) + if (!ent) return unpack_entry(p, base_offset, type, base_size); - ret = ent->data; - - if (!keep_cache) - clear_delta_base_cache_entry(ent); - else - ret = xmemdupz(ent->data, ent->size); *type = ent->type; *base_size = ent->size; - return ret; + return xmemdupz(ent->data, ent->size); } static inline void release_delta_base_cache(struct delta_base_cache_entry *ent) { - if (ent->data) { - free(ent->data); - ent->data = NULL; - ent->lru.next->prev = ent->lru.prev; - ent->lru.prev->next = ent->lru.next; - delta_base_cached -= ent->size; - } + free(ent->data); + detach_delta_base_cache_entry(ent); } 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]); + struct list_head *lru, *tmp; + list_for_each_safe(lru, tmp, &delta_base_cache_lru) { + struct delta_base_cache_entry *entry = + list_entry(lru, struct delta_base_cache_entry, lru); + release_delta_base_cache(entry); + } } static void add_delta_base_cache(struct packed_git *p, off_t base_offset, void *base, unsigned long base_size, enum object_type type) { - unsigned long hash = pack_entry_hash(p, base_offset); - struct delta_base_cache_entry *ent = delta_base_cache + hash; - struct delta_base_cache_lru_list *lru; + struct delta_base_cache_entry *ent = xmalloc(sizeof(*ent)); + struct list_head *lru, *tmp; - release_delta_base_cache(ent); delta_base_cached += base_size; - for (lru = delta_base_cache_lru.next; - delta_base_cached > delta_base_cache_limit - && lru != &delta_base_cache_lru; - lru = lru->next) { - struct delta_base_cache_entry *f = (void *)lru; - if (f->type == OBJ_BLOB) - release_delta_base_cache(f); - } - for (lru = delta_base_cache_lru.next; - delta_base_cached > delta_base_cache_limit - && lru != &delta_base_cache_lru; - lru = lru->next) { - struct delta_base_cache_entry *f = (void *)lru; + list_for_each_safe(lru, tmp, &delta_base_cache_lru) { + struct delta_base_cache_entry *f = + list_entry(lru, struct delta_base_cache_entry, lru); + if (delta_base_cached <= delta_base_cache_limit) + break; release_delta_base_cache(f); } - ent->p = p; - ent->base_offset = base_offset; + ent->key.p = p; + ent->key.base_offset = base_offset; ent->type = type; ent->data = base; ent->size = base_size; - ent->lru.next = &delta_base_cache_lru; - ent->lru.prev = delta_base_cache_lru.prev; - delta_base_cache_lru.prev->next = &ent->lru; - delta_base_cache_lru.prev = &ent->lru; + list_add_tail(&ent->lru, &delta_base_cache_lru); + + if (!delta_base_cache.cmpfn) + hashmap_init(&delta_base_cache, delta_base_cache_hash_cmp, 0); + hashmap_entry_init(ent, pack_entry_hash(p, base_offset)); + hashmap_add(&delta_base_cache, ent); } static void *read_object(const unsigned char *sha1, enum object_type *type, @@ -2270,11 +2449,11 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset, struct delta_base_cache_entry *ent; ent = get_delta_base_cache_entry(p, curpos); - if (eq_delta_base_cache_entry(ent, p, curpos)) { + if (ent) { type = ent->type; data = ent->data; size = ent->size; - clear_delta_base_cache_entry(ent); + detach_delta_base_cache_entry(ent); base_from_cache = 1; break; } @@ -2330,7 +2509,7 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset, case OBJ_OFS_DELTA: case OBJ_REF_DELTA: if (data) - die("BUG in unpack_entry: left loop at a valid delta"); + die("BUG: unpack_entry: left loop at a valid delta"); break; case OBJ_COMMIT: case OBJ_TREE: @@ -2604,21 +2783,15 @@ static int fill_pack_entry(const unsigned char *sha1, */ static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e) { - struct packed_git *p; + struct mru_entry *p; prepare_packed_git(); if (!packed_git) return 0; - if (last_found_pack && fill_pack_entry(sha1, e, last_found_pack)) - return 1; - - for (p = packed_git; p; p = p->next) { - if (p == last_found_pack) - continue; /* we already checked this one */ - - if (fill_pack_entry(sha1, e, p)) { - last_found_pack = p; + for (p = packed_git_mru->head; p; p = p->next) { + if (fill_pack_entry(sha1, e, p->item)) { + mru_mark(packed_git_mru, p); return 1; } } @@ -2661,8 +2834,9 @@ static int sha1_loose_object_info(const unsigned char *sha1, * object even exists. */ if (!oi->typep && !oi->typename && !oi->sizep) { + const char *path; struct stat st; - if (stat_sha1_file(sha1, &st) < 0) + if (stat_sha1_file(sha1, &st, &path) < 0) return -1; if (oi->disk_sizep) *oi->disk_sizep = st.st_size; @@ -2768,7 +2942,7 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi, int sha1_object_info(const unsigned char *sha1, unsigned long *sizep) { enum object_type type; - struct object_info oi = {NULL}; + struct object_info oi = OBJECT_INFO_INIT; oi.typep = &type; oi.sizep = sizep; @@ -2785,7 +2959,7 @@ static void *read_packed_sha1(const unsigned char *sha1, if (!find_pack_entry(sha1, &e)) return NULL; - data = cache_or_unpack_entry(e.p, e.offset, size, type, 1); + data = cache_or_unpack_entry(e.p, e.offset, size, type); if (!data) { /* * We're probably in deep shit, but let's try to fetch @@ -2858,6 +3032,8 @@ void *read_sha1_file_extended(const unsigned char *sha1, { void *data; const struct packed_git *p; + const char *path; + struct stat st; const unsigned char *repl = lookup_replace_object_extended(sha1, flag); errno = 0; @@ -2873,12 +3049,9 @@ void *read_sha1_file_extended(const unsigned char *sha1, die("replacement %s not found for %s", sha1_to_hex(repl), sha1_to_hex(sha1)); - if (has_loose_object(repl)) { - const char *path = sha1_file_name(sha1); - + if (!stat_sha1_file(repl, &st, &path)) die("loose object %s (stored in %s) is corrupt", sha1_to_hex(repl), path); - } if ((p = has_packed_and_bad(repl)) != NULL) die("packed object %s (stored in %s) is corrupt", @@ -3239,6 +3412,11 @@ int has_object_file(const struct object_id *oid) return has_sha1_file(oid->hash); } +int has_object_file_with_flags(const struct object_id *oid, int flags) +{ + return has_sha1_file_with_flags(oid->hash, flags); +} + static void check_tree(const void *buf, size_t size) { struct tree_desc desc; @@ -3578,8 +3756,7 @@ static int loose_from_alt_odb(struct alternate_object_database *alt, struct strbuf buf = STRBUF_INIT; int r; - /* copy base not including trailing '/' */ - strbuf_add(&buf, alt->base, alt->name - alt->base - 1); + strbuf_addstr(&buf, alt->path); r = for_each_loose_file_in_objdir_buf(&buf, data->cb, NULL, NULL, data->data); @@ -3644,3 +3821,122 @@ int for_each_packed_object(each_packed_object_fn cb, void *data, unsigned flags) } return r ? r : pack_errors; } + +static int check_stream_sha1(git_zstream *stream, + const char *hdr, + unsigned long size, + const char *path, + const unsigned char *expected_sha1) +{ + git_SHA_CTX c; + unsigned char real_sha1[GIT_SHA1_RAWSZ]; + unsigned char buf[4096]; + unsigned long total_read; + int status = Z_OK; + + git_SHA1_Init(&c); + git_SHA1_Update(&c, hdr, stream->total_out); + + /* + * We already read some bytes into hdr, but the ones up to the NUL + * do not count against the object's content size. + */ + total_read = stream->total_out - strlen(hdr) - 1; + + /* + * This size comparison must be "<=" to read the final zlib packets; + * see the comment in unpack_sha1_rest for details. + */ + while (total_read <= size && + (status == Z_OK || status == Z_BUF_ERROR)) { + stream->next_out = buf; + stream->avail_out = sizeof(buf); + if (size - total_read < stream->avail_out) + stream->avail_out = size - total_read; + status = git_inflate(stream, Z_FINISH); + git_SHA1_Update(&c, buf, stream->next_out - buf); + total_read += stream->next_out - buf; + } + git_inflate_end(stream); + + if (status != Z_STREAM_END) { + error("corrupt loose object '%s'", sha1_to_hex(expected_sha1)); + return -1; + } + if (stream->avail_in) { + error("garbage at end of loose object '%s'", + sha1_to_hex(expected_sha1)); + return -1; + } + + git_SHA1_Final(real_sha1, &c); + if (hashcmp(expected_sha1, real_sha1)) { + error("sha1 mismatch for %s (expected %s)", path, + sha1_to_hex(expected_sha1)); + return -1; + } + + return 0; +} + +int read_loose_object(const char *path, + const unsigned char *expected_sha1, + enum object_type *type, + unsigned long *size, + void **contents) +{ + int ret = -1; + int fd = -1; + void *map = NULL; + unsigned long mapsize; + git_zstream stream; + char hdr[32]; + + *contents = NULL; + + map = map_sha1_file_1(path, NULL, &mapsize); + if (!map) { + error_errno("unable to mmap %s", path); + goto out; + } + + if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0) { + error("unable to unpack header of %s", path); + goto out; + } + + *type = parse_sha1_header(hdr, size); + if (*type < 0) { + error("unable to parse header of %s", path); + git_inflate_end(&stream); + goto out; + } + + if (*type == OBJ_BLOB) { + if (check_stream_sha1(&stream, hdr, *size, path, expected_sha1) < 0) + goto out; + } else { + *contents = unpack_sha1_rest(&stream, hdr, *size, expected_sha1); + if (!*contents) { + error("unable to unpack contents of %s", path); + git_inflate_end(&stream); + goto out; + } + if (check_sha1_signature(expected_sha1, *contents, + *size, typename(*type))) { + error("sha1 mismatch for %s (expected %s)", path, + sha1_to_hex(expected_sha1)); + free(*contents); + goto out; + } + } + + ret = 0; /* everything checks out */ + +out: + if (map) + munmap(map, mapsize); + if (fd >= 0) + close(fd); + return ret; +} |