diff options
Diffstat (limited to 'object-file.c')
| -rw-r--r-- | object-file.c | 2125 |
1 files changed, 299 insertions, 1826 deletions
diff --git a/object-file.c b/object-file.c index 5b792b3dd4..2bc36ab3ee 100644 --- a/object-file.c +++ b/object-file.c @@ -8,492 +8,45 @@ */ #define USE_THE_REPOSITORY_VARIABLE -#define DISABLE_SIGN_COMPARE_WARNINGS #include "git-compat-util.h" -#include "abspath.h" -#include "config.h" +#include "bulk-checkin.h" #include "convert.h" +#include "dir.h" #include "environment.h" +#include "fsck.h" #include "gettext.h" #include "hex.h" -#include "string-list.h" -#include "lockfile.h" -#include "pack.h" -#include "commit.h" -#include "run-command.h" -#include "refs.h" -#include "bulk-checkin.h" -#include "repository.h" -#include "replace-object.h" -#include "streaming.h" -#include "dir.h" -#include "list.h" -#include "quote.h" -#include "packfile.h" +#include "loose.h" +#include "object-file-convert.h" #include "object-file.h" -#include "object-store.h" +#include "odb.h" #include "oidtree.h" +#include "pack.h" +#include "packfile.h" #include "path.h" -#include "promisor-remote.h" +#include "read-cache-ll.h" #include "setup.h" -#include "submodule.h" -#include "fsck.h" -#include "loose.h" -#include "object-file-convert.h" +#include "streaming.h" /* The maximum size for an object header. */ #define MAX_HEADER_LEN 32 -static const struct object_id empty_tree_oid = { - .hash = { - 0x4b, 0x82, 0x5d, 0xc6, 0x42, 0xcb, 0x6e, 0xb9, 0xa0, 0x60, - 0xe5, 0x4b, 0xf8, 0xd6, 0x92, 0x88, 0xfb, 0xee, 0x49, 0x04 - }, - .algo = GIT_HASH_SHA1, -}; -static const struct object_id empty_blob_oid = { - .hash = { - 0xe6, 0x9d, 0xe2, 0x9b, 0xb2, 0xd1, 0xd6, 0x43, 0x4b, 0x8b, - 0x29, 0xae, 0x77, 0x5a, 0xd8, 0xc2, 0xe4, 0x8c, 0x53, 0x91 - }, - .algo = GIT_HASH_SHA1, -}; -static const struct object_id null_oid_sha1 = { - .hash = {0}, - .algo = GIT_HASH_SHA1, -}; -static const struct object_id empty_tree_oid_sha256 = { - .hash = { - 0x6e, 0xf1, 0x9b, 0x41, 0x22, 0x5c, 0x53, 0x69, 0xf1, 0xc1, - 0x04, 0xd4, 0x5d, 0x8d, 0x85, 0xef, 0xa9, 0xb0, 0x57, 0xb5, - 0x3b, 0x14, 0xb4, 0xb9, 0xb9, 0x39, 0xdd, 0x74, 0xde, 0xcc, - 0x53, 0x21 - }, - .algo = GIT_HASH_SHA256, -}; -static const struct object_id empty_blob_oid_sha256 = { - .hash = { - 0x47, 0x3a, 0x0f, 0x4c, 0x3b, 0xe8, 0xa9, 0x36, 0x81, 0xa2, - 0x67, 0xe3, 0xb1, 0xe9, 0xa7, 0xdc, 0xda, 0x11, 0x85, 0x43, - 0x6f, 0xe1, 0x41, 0xf7, 0x74, 0x91, 0x20, 0xa3, 0x03, 0x72, - 0x18, 0x13 - }, - .algo = GIT_HASH_SHA256, -}; -static const struct object_id null_oid_sha256 = { - .hash = {0}, - .algo = GIT_HASH_SHA256, -}; - -static void git_hash_sha1_init(git_hash_ctx *ctx) -{ - git_SHA1_Init(&ctx->sha1); -} - -static void git_hash_sha1_clone(git_hash_ctx *dst, const git_hash_ctx *src) -{ - git_SHA1_Clone(&dst->sha1, &src->sha1); -} - -static void git_hash_sha1_update(git_hash_ctx *ctx, const void *data, size_t len) -{ - git_SHA1_Update(&ctx->sha1, data, len); -} - -static void git_hash_sha1_final(unsigned char *hash, git_hash_ctx *ctx) -{ - git_SHA1_Final(hash, &ctx->sha1); -} - -static void git_hash_sha1_final_oid(struct object_id *oid, git_hash_ctx *ctx) -{ - git_SHA1_Final(oid->hash, &ctx->sha1); - memset(oid->hash + GIT_SHA1_RAWSZ, 0, GIT_MAX_RAWSZ - GIT_SHA1_RAWSZ); - oid->algo = GIT_HASH_SHA1; -} - -static void git_hash_sha1_init_unsafe(git_hash_ctx *ctx) -{ - git_SHA1_Init_unsafe(&ctx->sha1_unsafe); -} - -static void git_hash_sha1_clone_unsafe(git_hash_ctx *dst, const git_hash_ctx *src) -{ - git_SHA1_Clone_unsafe(&dst->sha1_unsafe, &src->sha1_unsafe); -} - -static void git_hash_sha1_update_unsafe(git_hash_ctx *ctx, const void *data, - size_t len) -{ - git_SHA1_Update_unsafe(&ctx->sha1_unsafe, data, len); -} - -static void git_hash_sha1_final_unsafe(unsigned char *hash, git_hash_ctx *ctx) -{ - git_SHA1_Final_unsafe(hash, &ctx->sha1_unsafe); -} - -static void git_hash_sha1_final_oid_unsafe(struct object_id *oid, git_hash_ctx *ctx) -{ - git_SHA1_Final_unsafe(oid->hash, &ctx->sha1_unsafe); - memset(oid->hash + GIT_SHA1_RAWSZ, 0, GIT_MAX_RAWSZ - GIT_SHA1_RAWSZ); - oid->algo = GIT_HASH_SHA1; -} - -static void git_hash_sha256_init(git_hash_ctx *ctx) -{ - git_SHA256_Init(&ctx->sha256); -} - -static void git_hash_sha256_clone(git_hash_ctx *dst, const git_hash_ctx *src) -{ - git_SHA256_Clone(&dst->sha256, &src->sha256); -} - -static void git_hash_sha256_update(git_hash_ctx *ctx, const void *data, size_t len) -{ - git_SHA256_Update(&ctx->sha256, data, len); -} - -static void git_hash_sha256_final(unsigned char *hash, git_hash_ctx *ctx) -{ - git_SHA256_Final(hash, &ctx->sha256); -} - -static void git_hash_sha256_final_oid(struct object_id *oid, git_hash_ctx *ctx) -{ - git_SHA256_Final(oid->hash, &ctx->sha256); - /* - * This currently does nothing, so the compiler should optimize it out, - * but keep it in case we extend the hash size again. - */ - memset(oid->hash + GIT_SHA256_RAWSZ, 0, GIT_MAX_RAWSZ - GIT_SHA256_RAWSZ); - oid->algo = GIT_HASH_SHA256; -} - -static void git_hash_unknown_init(git_hash_ctx *ctx UNUSED) -{ - BUG("trying to init unknown hash"); -} - -static void git_hash_unknown_clone(git_hash_ctx *dst UNUSED, - const git_hash_ctx *src UNUSED) -{ - BUG("trying to clone unknown hash"); -} - -static void git_hash_unknown_update(git_hash_ctx *ctx UNUSED, - const void *data UNUSED, - size_t len UNUSED) -{ - BUG("trying to update unknown hash"); -} - -static void git_hash_unknown_final(unsigned char *hash UNUSED, - git_hash_ctx *ctx UNUSED) -{ - BUG("trying to finalize unknown hash"); -} - -static void git_hash_unknown_final_oid(struct object_id *oid UNUSED, - git_hash_ctx *ctx UNUSED) -{ - BUG("trying to finalize unknown hash"); -} - -const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = { - { - .name = NULL, - .format_id = 0x00000000, - .rawsz = 0, - .hexsz = 0, - .blksz = 0, - .init_fn = git_hash_unknown_init, - .clone_fn = git_hash_unknown_clone, - .update_fn = git_hash_unknown_update, - .final_fn = git_hash_unknown_final, - .final_oid_fn = git_hash_unknown_final_oid, - .unsafe_init_fn = git_hash_unknown_init, - .unsafe_clone_fn = git_hash_unknown_clone, - .unsafe_update_fn = git_hash_unknown_update, - .unsafe_final_fn = git_hash_unknown_final, - .unsafe_final_oid_fn = git_hash_unknown_final_oid, - .empty_tree = NULL, - .empty_blob = NULL, - .null_oid = NULL, - }, - { - .name = "sha1", - .format_id = GIT_SHA1_FORMAT_ID, - .rawsz = GIT_SHA1_RAWSZ, - .hexsz = GIT_SHA1_HEXSZ, - .blksz = GIT_SHA1_BLKSZ, - .init_fn = git_hash_sha1_init, - .clone_fn = git_hash_sha1_clone, - .update_fn = git_hash_sha1_update, - .final_fn = git_hash_sha1_final, - .final_oid_fn = git_hash_sha1_final_oid, - .unsafe_init_fn = git_hash_sha1_init_unsafe, - .unsafe_clone_fn = git_hash_sha1_clone_unsafe, - .unsafe_update_fn = git_hash_sha1_update_unsafe, - .unsafe_final_fn = git_hash_sha1_final_unsafe, - .unsafe_final_oid_fn = git_hash_sha1_final_oid_unsafe, - .empty_tree = &empty_tree_oid, - .empty_blob = &empty_blob_oid, - .null_oid = &null_oid_sha1, - }, - { - .name = "sha256", - .format_id = GIT_SHA256_FORMAT_ID, - .rawsz = GIT_SHA256_RAWSZ, - .hexsz = GIT_SHA256_HEXSZ, - .blksz = GIT_SHA256_BLKSZ, - .init_fn = git_hash_sha256_init, - .clone_fn = git_hash_sha256_clone, - .update_fn = git_hash_sha256_update, - .final_fn = git_hash_sha256_final, - .final_oid_fn = git_hash_sha256_final_oid, - .unsafe_init_fn = git_hash_sha256_init, - .unsafe_clone_fn = git_hash_sha256_clone, - .unsafe_update_fn = git_hash_sha256_update, - .unsafe_final_fn = git_hash_sha256_final, - .unsafe_final_oid_fn = git_hash_sha256_final_oid, - .empty_tree = &empty_tree_oid_sha256, - .empty_blob = &empty_blob_oid_sha256, - .null_oid = &null_oid_sha256, - } -}; - -const struct object_id *null_oid(void) -{ - return the_hash_algo->null_oid; -} - -const char *empty_tree_oid_hex(const struct git_hash_algo *algop) -{ - static char buf[GIT_MAX_HEXSZ + 1]; - return oid_to_hex_r(buf, algop->empty_tree); -} - -int hash_algo_by_name(const char *name) -{ - int i; - if (!name) - return GIT_HASH_UNKNOWN; - for (i = 1; i < GIT_HASH_NALGOS; i++) - if (!strcmp(name, hash_algos[i].name)) - return i; - return GIT_HASH_UNKNOWN; -} - -int hash_algo_by_id(uint32_t format_id) -{ - int i; - for (i = 1; i < GIT_HASH_NALGOS; i++) - if (format_id == hash_algos[i].format_id) - return i; - return GIT_HASH_UNKNOWN; -} - -int hash_algo_by_length(int len) -{ - int i; - for (i = 1; i < GIT_HASH_NALGOS; i++) - if (len == hash_algos[i].rawsz) - return i; - return GIT_HASH_UNKNOWN; -} - -/* - * This is meant to hold a *small* number of objects that you would - * want repo_read_object_file() to be able to return, but yet you do not want - * to write them into the object store (e.g. a browse-only - * application). - */ -static struct cached_object_entry { - struct object_id oid; - struct cached_object { - enum object_type type; - const void *buf; - unsigned long size; - } value; -} *cached_objects; -static int cached_object_nr, cached_object_alloc; - -static const struct cached_object *find_cached_object(const struct object_id *oid) -{ - static const struct cached_object empty_tree = { - .type = OBJ_TREE, - .buf = "", - }; - int i; - const struct cached_object_entry *co = cached_objects; - - for (i = 0; i < cached_object_nr; i++, co++) { - if (oideq(&co->oid, oid)) - return &co->value; - } - if (oideq(oid, the_hash_algo->empty_tree)) - return &empty_tree; - return NULL; -} - - static int get_conv_flags(unsigned flags) { - if (flags & HASH_RENORMALIZE) + if (flags & INDEX_RENORMALIZE) return CONV_EOL_RENORMALIZE; - else if (flags & HASH_WRITE_OBJECT) + else if (flags & INDEX_WRITE_OBJECT) return global_conv_flags_eol | CONV_WRITE_OBJECT; else return 0; } - -int mkdir_in_gitdir(const char *path) -{ - if (mkdir(path, 0777)) { - int saved_errno = errno; - struct stat st; - struct strbuf sb = STRBUF_INIT; - - if (errno != EEXIST) - return -1; - /* - * Are we looking at a path in a symlinked worktree - * whose original repository does not yet have it? - * e.g. .git/rr-cache pointing at its original - * repository in which the user hasn't performed any - * conflict resolution yet? - */ - if (lstat(path, &st) || !S_ISLNK(st.st_mode) || - strbuf_readlink(&sb, path, st.st_size) || - !is_absolute_path(sb.buf) || - mkdir(sb.buf, 0777)) { - strbuf_release(&sb); - errno = saved_errno; - return -1; - } - strbuf_release(&sb); - } - return adjust_shared_perm(path); -} - -static enum scld_error safe_create_leading_directories_1(char *path, int share) -{ - char *next_component = path + offset_1st_component(path); - enum scld_error ret = SCLD_OK; - - while (ret == SCLD_OK && next_component) { - struct stat st; - char *slash = next_component, slash_character; - - while (*slash && !is_dir_sep(*slash)) - slash++; - - if (!*slash) - break; - - next_component = slash + 1; - while (is_dir_sep(*next_component)) - next_component++; - if (!*next_component) - break; - - slash_character = *slash; - *slash = '\0'; - if (!stat(path, &st)) { - /* path exists */ - if (!S_ISDIR(st.st_mode)) { - errno = ENOTDIR; - ret = SCLD_EXISTS; - } - } else if (mkdir(path, 0777)) { - if (errno == EEXIST && - !stat(path, &st) && S_ISDIR(st.st_mode)) - ; /* somebody created it since we checked */ - else if (errno == ENOENT) - /* - * Either mkdir() failed because - * somebody just pruned the containing - * directory, or stat() failed because - * the file that was in our way was - * just removed. Either way, inform - * the caller that it might be worth - * trying again: - */ - ret = SCLD_VANISHED; - else - ret = SCLD_FAILED; - } else if (share && adjust_shared_perm(path)) { - ret = SCLD_PERMS; - } - *slash = slash_character; - } - return ret; -} - -enum scld_error safe_create_leading_directories(char *path) -{ - return safe_create_leading_directories_1(path, 1); -} - -enum scld_error safe_create_leading_directories_no_share(char *path) -{ - return safe_create_leading_directories_1(path, 0); -} - -enum scld_error safe_create_leading_directories_const(const char *path) -{ - int save_errno; - /* path points to cache entries, so xstrdup before messing with it */ - char *buf = xstrdup(path); - enum scld_error result = safe_create_leading_directories(buf); - - save_errno = errno; - free(buf); - errno = save_errno; - return result; -} - -int odb_mkstemp(struct strbuf *temp_filename, const char *pattern) -{ - int fd; - /* - * we let the umask do its job, don't try to be more - * restrictive except to remove write permission. - */ - int mode = 0444; - git_path_buf(temp_filename, "objects/%s", pattern); - fd = git_mkstemp_mode(temp_filename->buf, mode); - if (0 <= fd) - return fd; - - /* slow path */ - /* some mkstemp implementations erase temp_filename on failure */ - git_path_buf(temp_filename, "objects/%s", pattern); - safe_create_leading_directories(temp_filename->buf); - return xmkstemp_mode(temp_filename->buf, mode); -} - -int odb_pack_keep(const char *name) -{ - int fd; - - fd = open(name, O_RDWR|O_CREAT|O_EXCL, 0600); - if (0 <= fd) - return fd; - - /* slow path */ - safe_create_leading_directories_const(name); - return open(name, O_RDWR|O_CREAT|O_EXCL, 0600); -} - -static void fill_loose_path(struct strbuf *buf, const struct object_id *oid) +static void fill_loose_path(struct strbuf *buf, + const struct object_id *oid, + const struct git_hash_algo *algop) { - int i; - for (i = 0; i < the_hash_algo->rawsz; i++) { + for (size_t i = 0; i < algop->rawsz; i++) { static char hex[] = "0123456789abcdef"; unsigned int val = oid->hash[i]; strbuf_addch(buf, hex[val >> 4]); @@ -503,524 +56,17 @@ static void fill_loose_path(struct strbuf *buf, const struct object_id *oid) } } -static const char *odb_loose_path(struct object_directory *odb, - struct strbuf *buf, - const struct object_id *oid) +const char *odb_loose_path(struct odb_source *source, + struct strbuf *buf, + const struct object_id *oid) { strbuf_reset(buf); - strbuf_addstr(buf, odb->path); + strbuf_addstr(buf, source->path); strbuf_addch(buf, '/'); - fill_loose_path(buf, oid); + fill_loose_path(buf, oid, source->odb->repo->hash_algo); return buf->buf; } -const char *loose_object_path(struct repository *r, struct strbuf *buf, - const struct object_id *oid) -{ - return odb_loose_path(r->objects->odb, buf, oid); -} - -/* - * Return non-zero iff the path is usable as an alternate object database. - */ -static int alt_odb_usable(struct raw_object_store *o, - struct strbuf *path, - const char *normalized_objdir, khiter_t *pos) -{ - int r; - - /* 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. - */ - if (!o->odb_by_path) { - khiter_t p; - - o->odb_by_path = kh_init_odb_path_map(); - assert(!o->odb->next); - p = kh_put_odb_path_map(o->odb_by_path, o->odb->path, &r); - assert(r == 1); /* never used */ - kh_value(o->odb_by_path, p) = o->odb; - } - if (fspatheq(path->buf, normalized_objdir)) - return 0; - *pos = kh_put_odb_path_map(o->odb_by_path, path->buf, &r); - /* r: 0 = exists, 1 = never used, 2 = deleted */ - return r == 0 ? 0 : 1; -} - -/* - * Prepare alternate object database registry. - * - * The variable alt_odb_list points at the list of struct - * object_directory. The elements on this list come from - * non-empty elements from colon separated ALTERNATE_DB_ENVIRONMENT - * environment variable, and $GIT_OBJECT_DIRECTORY/info/alternates, - * whose contents is similar to that environment variable but can be - * LF separated. Its base points at a statically allocated buffer that - * contains "/the/directory/corresponding/to/.git/objects/...", while - * its name points just after the slash at the end of ".git/objects/" - * in the example above, and has enough space to hold all hex characters - * of the object ID, an extra slash for the first level indirection, and - * the terminating NUL. - */ -static void read_info_alternates(struct repository *r, - const char *relative_base, - int depth); -static int link_alt_odb_entry(struct repository *r, const struct strbuf *entry, - const char *relative_base, int depth, const char *normalized_objdir) -{ - struct object_directory *ent; - struct strbuf pathbuf = STRBUF_INIT; - struct strbuf tmp = STRBUF_INIT; - khiter_t pos; - int ret = -1; - - if (!is_absolute_path(entry->buf) && relative_base) { - strbuf_realpath(&pathbuf, relative_base, 1); - strbuf_addch(&pathbuf, '/'); - } - strbuf_addbuf(&pathbuf, entry); - - if (!strbuf_realpath(&tmp, pathbuf.buf, 0)) { - error(_("unable to normalize alternate object path: %s"), - pathbuf.buf); - goto error; - } - strbuf_swap(&pathbuf, &tmp); - - /* - * The trailing slash after the directory name is given by - * this function at the end. Remove duplicates. - */ - while (pathbuf.len && pathbuf.buf[pathbuf.len - 1] == '/') - strbuf_setlen(&pathbuf, pathbuf.len - 1); - - if (!alt_odb_usable(r->objects, &pathbuf, normalized_objdir, &pos)) - goto error; - - CALLOC_ARRAY(ent, 1); - /* pathbuf.buf is already in r->objects->odb_by_path */ - ent->path = strbuf_detach(&pathbuf, NULL); - - /* add the alternate entry */ - *r->objects->odb_tail = ent; - r->objects->odb_tail = &(ent->next); - ent->next = NULL; - assert(r->objects->odb_by_path); - kh_value(r->objects->odb_by_path, pos) = ent; - - /* recursively add alternates */ - read_info_alternates(r, ent->path, depth + 1); - ret = 0; - error: - strbuf_release(&tmp); - strbuf_release(&pathbuf); - return ret; -} - -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(struct repository *r, const char *alt, - int sep, const char *relative_base, int depth) -{ - struct strbuf objdirbuf = STRBUF_INIT; - struct strbuf entry = STRBUF_INIT; - - if (!alt || !*alt) - return; - - if (depth > 5) { - error(_("%s: ignoring alternate object stores, nesting too deep"), - relative_base); - return; - } - - strbuf_realpath(&objdirbuf, r->objects->odb->path, 1); - - while (*alt) { - alt = parse_alt_odb_entry(alt, sep, &entry); - if (!entry.len) - continue; - link_alt_odb_entry(r, &entry, - relative_base, depth, objdirbuf.buf); - } - strbuf_release(&entry); - strbuf_release(&objdirbuf); -} - -static void read_info_alternates(struct repository *r, - const char *relative_base, - int depth) -{ - char *path; - struct strbuf buf = STRBUF_INIT; - - path = xstrfmt("%s/info/alternates", relative_base); - if (strbuf_read_file(&buf, path, 1024) < 0) { - warn_on_fopen_errors(path); - free(path); - return; - } - - link_alt_odb_entries(r, buf.buf, '\n', relative_base, depth); - strbuf_release(&buf); - free(path); -} - -void add_to_alternates_file(const char *reference) -{ - struct lock_file lock = LOCK_INIT; - char *alts = git_pathdup("objects/info/alternates"); - FILE *in, *out; - int found = 0; - - hold_lock_file_for_update(&lock, alts, LOCK_DIE_ON_ERROR); - out = fdopen_lock_file(&lock, "w"); - if (!out) - die_errno(_("unable to fdopen alternates lockfile")); - - in = fopen(alts, "r"); - if (in) { - struct strbuf line = STRBUF_INIT; - - while (strbuf_getline(&line, in) != EOF) { - if (!strcmp(reference, line.buf)) { - found = 1; - break; - } - fprintf_or_die(out, "%s\n", line.buf); - } - - strbuf_release(&line); - fclose(in); - } - else if (errno != ENOENT) - die_errno(_("unable to read alternates file")); - - if (found) { - rollback_lock_file(&lock); - } else { - fprintf_or_die(out, "%s\n", reference); - if (commit_lock_file(&lock)) - die_errno(_("unable to move new alternates file into place")); - if (the_repository->objects->loaded_alternates) - link_alt_odb_entries(the_repository, reference, - '\n', NULL, 0); - } - 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(the_repository); - - link_alt_odb_entries(the_repository, reference, - '\n', NULL, 0); -} - -struct object_directory *set_temporary_primary_odb(const char *dir, int will_destroy) -{ - struct object_directory *new_odb; - - /* - * Make sure alternates are initialized, or else our entry may be - * overwritten when they are. - */ - prepare_alt_odb(the_repository); - - /* - * Make a new primary odb and link the old primary ODB in as an - * alternate - */ - new_odb = xcalloc(1, sizeof(*new_odb)); - new_odb->path = xstrdup(dir); - - /* - * Disable ref updates while a temporary odb is active, since - * the objects in the database may roll back. - */ - new_odb->disable_ref_updates = 1; - new_odb->will_destroy = will_destroy; - new_odb->next = the_repository->objects->odb; - the_repository->objects->odb = new_odb; - return new_odb->next; -} - -void restore_primary_odb(struct object_directory *restore_odb, const char *old_path) -{ - struct object_directory *cur_odb = the_repository->objects->odb; - - if (strcmp(old_path, cur_odb->path)) - BUG("expected %s as primary object store; found %s", - old_path, cur_odb->path); - - if (cur_odb->next != restore_odb) - BUG("we expect the old primary object store to be the first alternate"); - - the_repository->objects->odb = restore_odb; - free_object_directory(cur_odb); -} - -/* - * 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 $GIT_DIR. - * `err` must not be null. - */ -char *compute_alternate_path(const char *path, struct strbuf *err) -{ - char *ref_git = NULL; - const char *repo; - int seen_error = 0; - - ref_git = real_pathdup(path, 0); - if (!ref_git) { - seen_error = 1; - strbuf_addf(err, _("path '%s' does not exist"), path); - goto out; - } - - 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_AND_NULL(ref_git); - } - - return ref_git; -} - -struct object_directory *find_odb(struct repository *r, const char *obj_dir) -{ - struct object_directory *odb; - char *obj_dir_real = real_pathdup(obj_dir, 1); - struct strbuf odb_path_real = STRBUF_INIT; - - prepare_alt_odb(r); - for (odb = r->objects->odb; odb; odb = odb->next) { - strbuf_realpath(&odb_path_real, odb->path, 1); - if (!strcmp(obj_dir_real, odb_path_real.buf)) - break; - } - - free(obj_dir_real); - strbuf_release(&odb_path_real); - - if (!odb) - die(_("could not find object directory matching %s"), obj_dir); - return odb; -} - -static void fill_alternate_refs_command(struct child_process *cmd, - const char *repo_path) -{ - const char *value; - - if (!git_config_get_value("core.alternateRefsCommand", &value)) { - cmd->use_shell = 1; - - strvec_push(&cmd->args, value); - strvec_push(&cmd->args, repo_path); - } else { - cmd->git_cmd = 1; - - strvec_pushf(&cmd->args, "--git-dir=%s", repo_path); - strvec_push(&cmd->args, "for-each-ref"); - strvec_push(&cmd->args, "--format=%(objectname)"); - - if (!git_config_get_value("core.alternateRefsPrefixes", &value)) { - strvec_push(&cmd->args, "--"); - strvec_split(&cmd->args, value); - } - } - - strvec_pushv(&cmd->env, (const char **)local_repo_env); - cmd->out = -1; -} - -static void read_alternate_refs(const char *path, - alternate_ref_fn *cb, - void *data) -{ - struct child_process cmd = CHILD_PROCESS_INIT; - struct strbuf line = STRBUF_INIT; - FILE *fh; - - fill_alternate_refs_command(&cmd, path); - - if (start_command(&cmd)) - return; - - fh = xfdopen(cmd.out, "r"); - while (strbuf_getline_lf(&line, fh) != EOF) { - struct object_id oid; - const char *p; - - if (parse_oid_hex(line.buf, &oid, &p) || *p) { - warning(_("invalid line while parsing alternate refs: %s"), - line.buf); - break; - } - - cb(&oid, data); - } - - fclose(fh); - finish_command(&cmd); - strbuf_release(&line); -} - -struct alternate_refs_data { - alternate_ref_fn *fn; - void *data; -}; - -static int refs_from_alternate_cb(struct object_directory *e, - void *data) -{ - struct strbuf path = STRBUF_INIT; - size_t base_len; - struct alternate_refs_data *cb = data; - - if (!strbuf_realpath(&path, e->path, 0)) - goto out; - if (!strbuf_strip_suffix(&path, "/objects")) - goto out; - base_len = path.len; - - /* Is this a git repository with refs? */ - strbuf_addstr(&path, "/refs"); - if (!is_directory(path.buf)) - goto out; - strbuf_setlen(&path, base_len); - - read_alternate_refs(path.buf, cb->fn, cb->data); - -out: - strbuf_release(&path); - return 0; -} - -void for_each_alternate_ref(alternate_ref_fn fn, void *data) -{ - struct alternate_refs_data cb; - cb.fn = fn; - cb.data = data; - foreach_alt_odb(refs_from_alternate_cb, &cb); -} - -int foreach_alt_odb(alt_odb_fn fn, void *cb) -{ - struct object_directory *ent; - int r = 0; - - prepare_alt_odb(the_repository); - for (ent = the_repository->objects->odb->next; ent; ent = ent->next) { - r = fn(ent, cb); - if (r) - break; - } - return r; -} - -void prepare_alt_odb(struct repository *r) -{ - if (r->objects->loaded_alternates) - return; - - link_alt_odb_entries(r, r->objects->alternate_db, PATH_SEP, NULL, 0); - - read_info_alternates(r, r->objects->odb->path, 0); - r->objects->loaded_alternates = 1; -} - -int has_alt_odb(struct repository *r) -{ - prepare_alt_odb(r); - return !!r->objects->odb->next; -} - /* Returns 1 if we have successfully freshened the file, 0 otherwise. */ static int freshen_file(const char *fn) { @@ -1043,100 +89,19 @@ int check_and_freshen_file(const char *fn, int freshen) return 1; } -static int check_and_freshen_odb(struct object_directory *odb, - const struct object_id *oid, - int freshen) +static int check_and_freshen_source(struct odb_source *source, + const struct object_id *oid, + int freshen) { static struct strbuf path = STRBUF_INIT; - odb_loose_path(odb, &path, oid); + odb_loose_path(source, &path, oid); return check_and_freshen_file(path.buf, freshen); } -static int check_and_freshen_local(const struct object_id *oid, int freshen) -{ - return check_and_freshen_odb(the_repository->objects->odb, oid, freshen); -} - -static int check_and_freshen_nonlocal(const struct object_id *oid, int freshen) +int has_loose_object(struct odb_source *source, + const struct object_id *oid) { - struct object_directory *odb; - - prepare_alt_odb(the_repository); - for (odb = the_repository->objects->odb->next; odb; odb = odb->next) { - if (check_and_freshen_odb(odb, oid, freshen)) - return 1; - } - return 0; -} - -static int check_and_freshen(const struct object_id *oid, int freshen) -{ - return check_and_freshen_local(oid, freshen) || - check_and_freshen_nonlocal(oid, freshen); -} - -int has_loose_object_nonlocal(const struct object_id *oid) -{ - return check_and_freshen_nonlocal(oid, 0); -} - -int has_loose_object(const struct object_id *oid) -{ - return check_and_freshen(oid, 0); -} - -static void mmap_limit_check(size_t length) -{ - static size_t limit = 0; - if (!limit) { - limit = git_env_ulong("GIT_MMAP_LIMIT", 0); - if (!limit) - limit = SIZE_MAX; - } - if (length > limit) - die(_("attempting to mmap %"PRIuMAX" over limit %"PRIuMAX), - (uintmax_t)length, (uintmax_t)limit); -} - -void *xmmap_gently(void *start, size_t length, - int prot, int flags, int fd, off_t offset) -{ - void *ret; - - mmap_limit_check(length); - ret = mmap(start, length, prot, flags, fd, offset); - if (ret == MAP_FAILED && !length) - ret = NULL; - return ret; -} - -const char *mmap_os_err(void) -{ - static const char blank[] = ""; -#if defined(__linux__) - if (errno == ENOMEM) { - /* this continues an existing error message: */ - static const char enomem[] = -", check sys.vm.max_map_count and/or RLIMIT_DATA"; - return enomem; - } -#endif /* OS-specific bits */ - return blank; -} - -void *xmmap(void *start, size_t length, - int prot, int flags, int fd, off_t offset) -{ - void *ret = xmmap_gently(start, length, prot, flags, fd, offset); - if (ret == MAP_FAILED) - die_errno(_("mmap failed%s"), mmap_os_err()); - return ret; -} - -static int format_object_header_literally(char *str, size_t size, - const char *type, size_t objsize) -{ - return xsnprintf(str, size, "%s %"PRIuMAX, type, (uintmax_t)objsize) + 1; + return check_and_freshen_source(source, oid, 0); } int format_object_header(char *str, size_t size, enum object_type type, @@ -1147,7 +112,7 @@ int format_object_header(char *str, size_t size, enum object_type type, if (!name) BUG("could not get a type name for 'enum object_type' value %d", type); - return format_object_header_literally(str, size, name, objsize); + return xsnprintf(str, size, "%s %"PRIuMAX, name, (uintmax_t)objsize) + 1; } int check_object_signature(struct repository *r, const struct object_id *oid, @@ -1169,7 +134,7 @@ int stream_object_signature(struct repository *r, const struct object_id *oid) unsigned long size; enum object_type obj_type; struct git_istream *st; - git_hash_ctx c; + struct git_hash_ctx c; char hdr[MAX_HEADER_LEN]; int hdrlen; @@ -1182,7 +147,7 @@ int stream_object_signature(struct repository *r, const struct object_id *oid) /* Sha1.. */ r->hash_algo->init_fn(&c); - r->hash_algo->update_fn(&c, hdr, hdrlen); + git_hash_update(&c, hdr, hdrlen); for (;;) { char buf[1024 * 16]; ssize_t readlen = read_istream(st, buf, sizeof(buf)); @@ -1193,40 +158,13 @@ int stream_object_signature(struct repository *r, const struct object_id *oid) } if (!readlen) break; - r->hash_algo->update_fn(&c, buf, readlen); + git_hash_update(&c, buf, readlen); } - r->hash_algo->final_oid_fn(&real_oid, &c); + git_hash_final_oid(&real_oid, &c); close_istream(st); return !oideq(oid, &real_oid) ? -1 : 0; } -int git_open_cloexec(const char *name, int flags) -{ - int fd; - static int o_cloexec = O_CLOEXEC; - - 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); - } - -#if defined(F_GETFD) && defined(F_SETFD) && defined(FD_CLOEXEC) - { - static int fd_cloexec = FD_CLOEXEC; - - if (!o_cloexec && 0 <= fd && fd_cloexec) { - /* Opened w/o O_CLOEXEC? try with fcntl(2) to add it */ - int flags = fcntl(fd, F_GETFD); - if (fcntl(fd, F_SETFD, flags | fd_cloexec)) - fd_cloexec = 0; - } - } -#endif - return fd; -} - /* * Find "oid" as a loose object in the local repository or in an alternate. * Returns 0 on success, negative on failure. @@ -1238,12 +176,12 @@ int git_open_cloexec(const char *name, int flags) static int stat_loose_object(struct repository *r, const struct object_id *oid, struct stat *st, const char **path) { - struct object_directory *odb; + struct odb_source *source; static struct strbuf buf = STRBUF_INIT; - prepare_alt_odb(r); - for (odb = r->objects->odb; odb; odb = odb->next) { - *path = odb_loose_path(odb, &buf, oid); + odb_prepare_alternates(r->objects); + for (source = r->objects->sources; source; source = source->next) { + *path = odb_loose_path(source, &buf, oid); if (!lstat(*path, st)) return 0; } @@ -1259,13 +197,13 @@ static int open_loose_object(struct repository *r, const struct object_id *oid, const char **path) { int fd; - struct object_directory *odb; + struct odb_source *source; int most_interesting_errno = ENOENT; static struct strbuf buf = STRBUF_INIT; - prepare_alt_odb(r); - for (odb = r->objects->odb; odb; odb = odb->next) { - *path = odb_loose_path(odb, &buf, oid); + odb_prepare_alternates(r->objects); + for (source = r->objects->sources; source; source = source->next) { + *path = odb_loose_path(source, &buf, oid); fd = git_open(*path); if (fd >= 0) return fd; @@ -1280,11 +218,11 @@ static int open_loose_object(struct repository *r, static int quick_has_loose(struct repository *r, const struct object_id *oid) { - struct object_directory *odb; + struct odb_source *source; - prepare_alt_odb(r); - for (odb = r->objects->odb; odb; odb = odb->next) { - if (oidtree_contains(odb_loose_cache(odb, oid), oid)) + odb_prepare_alternates(r->objects); + for (source = r->objects->sources; source; source = source->next) { + if (oidtree_contains(odb_loose_cache(source, oid), oid)) return 1; } return 0; @@ -1329,8 +267,7 @@ enum unpack_loose_header_result unpack_loose_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, - unsigned long bufsiz, - struct strbuf *header) + unsigned long bufsiz) { int status; @@ -1345,7 +282,7 @@ enum unpack_loose_header_result unpack_loose_header(git_zstream *stream, obj_read_unlock(); status = git_inflate(stream, 0); obj_read_lock(); - if (status < Z_OK) + if (status != Z_OK && status != Z_STREAM_END) return ULHR_BAD; /* @@ -1355,32 +292,8 @@ enum unpack_loose_header_result unpack_loose_header(git_zstream *stream, return ULHR_OK; /* - * We have a header longer than MAX_HEADER_LEN. The "header" - * here is only non-NULL when we run "cat-file - * --allow-unknown-type". + * We have a header longer than MAX_HEADER_LEN. */ - if (!header) - return ULHR_TOO_LONG; - - /* - * buffer[0..bufsiz] was not large enough. Copy the partial - * result out to header, and then append the result of further - * reading the stream. - */ - strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer); - stream->next_out = buffer; - stream->avail_out = bufsiz; - - do { - obj_read_unlock(); - status = git_inflate(stream, 0); - obj_read_lock(); - strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer); - if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer)) - return 0; - stream->next_out = buffer; - stream->avail_out = bufsiz; - } while (status != Z_STREAM_END); return ULHR_TOO_LONG; } @@ -1388,9 +301,8 @@ static void *unpack_loose_rest(git_zstream *stream, void *buffer, unsigned long size, const struct object_id *oid) { - int bytes = strlen(buffer) + 1; + size_t bytes = strlen(buffer) + 1, n; unsigned char *buf = xmallocz(size); - unsigned long n; int status = Z_OK; n = stream->total_out - bytes; @@ -1420,18 +332,17 @@ static void *unpack_loose_rest(git_zstream *stream, obj_read_lock(); } } - if (status == Z_STREAM_END && !stream->avail_in) { - git_inflate_end(stream); - return buf; - } - if (status < 0) + if (status != Z_STREAM_END) { error(_("corrupt loose object '%s'"), oid_to_hex(oid)); - else if (stream->avail_in) + FREE_AND_NULL(buf); + } else if (stream->avail_in) { error(_("garbage at end of loose object '%s'"), oid_to_hex(oid)); - free(buf); - return NULL; + FREE_AND_NULL(buf); + } + + return buf; } /* @@ -1459,8 +370,6 @@ int parse_loose_header(const char *hdr, struct object_info *oi) } type = type_from_string_gently(type_buf, type_len, 1); - if (oi->type_name) - strbuf_add(oi->type_name, type_buf, type_len); if (oi->typep) *oi->typep = type; @@ -1497,9 +406,9 @@ int parse_loose_header(const char *hdr, struct object_info *oi) return 0; } -static int loose_object_info(struct repository *r, - const struct object_id *oid, - struct object_info *oi, int flags) +int loose_object_info(struct repository *r, + const struct object_id *oid, + struct object_info *oi, int flags) { int status = 0; int fd; @@ -1508,13 +417,11 @@ static int loose_object_info(struct repository *r, void *map; git_zstream stream; char hdr[MAX_HEADER_LEN]; - struct strbuf hdrbuf = STRBUF_INIT; unsigned long size_scratch; enum object_type type_scratch; - int allow_unknown = flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE; if (oi->delta_base_oid) - oidclr(oi->delta_base_oid, the_repository->hash_algo); + oidclr(oi->delta_base_oid, r->hash_algo); /* * If we don't care about type or size, then we don't @@ -1524,7 +431,7 @@ static int loose_object_info(struct repository *r, * return value implicitly indicates whether the * object even exists. */ - if (!oi->typep && !oi->type_name && !oi->sizep && !oi->contentp) { + if (!oi->typep && !oi->sizep && !oi->contentp) { struct stat st; if (!oi->disk_sizep && (flags & OBJECT_INFO_QUICK)) return quick_has_loose(r, oid) ? 0 : -1; @@ -1553,12 +460,11 @@ static int loose_object_info(struct repository *r, if (oi->disk_sizep) *oi->disk_sizep = mapsize; - switch (unpack_loose_header(&stream, map, mapsize, hdr, sizeof(hdr), - allow_unknown ? &hdrbuf : NULL)) { + switch (unpack_loose_header(&stream, map, mapsize, hdr, sizeof(hdr))) { case ULHR_OK: - if (parse_loose_header(hdrbuf.len ? hdrbuf.buf : hdr, oi) < 0) + if (parse_loose_header(hdr, oi) < 0) status = error(_("unable to parse %s header"), oid_to_hex(oid)); - else if (!allow_unknown && *oi->typep < 0) + else if (*oi->typep < 0) die(_("invalid object type")); if (!oi->contentp) @@ -1583,366 +489,26 @@ static int loose_object_info(struct repository *r, die(_("loose object %s (stored in %s) is corrupt"), oid_to_hex(oid), path); - git_inflate_end(&stream); cleanup: + git_inflate_end(&stream); munmap(map, mapsize); if (oi->sizep == &size_scratch) oi->sizep = NULL; - strbuf_release(&hdrbuf); if (oi->typep == &type_scratch) oi->typep = NULL; oi->whence = OI_LOOSE; return status; } -int obj_read_use_lock = 0; -pthread_mutex_t obj_read_mutex; - -void enable_obj_read_lock(void) -{ - if (obj_read_use_lock) - return; - - obj_read_use_lock = 1; - init_recursive_mutex(&obj_read_mutex); -} - -void disable_obj_read_lock(void) -{ - if (!obj_read_use_lock) - return; - - obj_read_use_lock = 0; - pthread_mutex_destroy(&obj_read_mutex); -} - -int fetch_if_missing = 1; - -static int do_oid_object_info_extended(struct repository *r, - const struct object_id *oid, - struct object_info *oi, unsigned flags) -{ - static struct object_info blank_oi = OBJECT_INFO_INIT; - const struct cached_object *co; - struct pack_entry e; - int rtype; - const struct object_id *real = oid; - int already_retried = 0; - - - if (flags & OBJECT_INFO_LOOKUP_REPLACE) - real = lookup_replace_object(r, oid); - - if (is_null_oid(real)) - return -1; - - if (!oi) - oi = &blank_oi; - - co = find_cached_object(real); - if (co) { - if (oi->typep) - *(oi->typep) = co->type; - if (oi->sizep) - *(oi->sizep) = co->size; - if (oi->disk_sizep) - *(oi->disk_sizep) = 0; - if (oi->delta_base_oid) - oidclr(oi->delta_base_oid, the_repository->hash_algo); - if (oi->type_name) - strbuf_addstr(oi->type_name, type_name(co->type)); - if (oi->contentp) - *oi->contentp = xmemdupz(co->buf, co->size); - oi->whence = OI_CACHED; - return 0; - } - - while (1) { - if (find_pack_entry(r, real, &e)) - break; - - /* Most likely it's a loose object. */ - if (!loose_object_info(r, real, oi, flags)) - return 0; - - /* Not a loose object; someone else may have just packed it. */ - if (!(flags & OBJECT_INFO_QUICK)) { - reprepare_packed_git(r); - if (find_pack_entry(r, real, &e)) - break; - } - - /* - * If r is the_repository, this might be an attempt at - * accessing a submodule object as if it were in the_repository - * (having called add_submodule_odb() on that submodule's ODB). - * If any such ODBs exist, register them and try again. - */ - if (r == the_repository && - register_all_submodule_odb_as_alternates()) - /* We added some alternates; retry */ - continue; - - /* Check if it is a missing object */ - if (fetch_if_missing && repo_has_promisor_remote(r) && - !already_retried && - !(flags & OBJECT_INFO_SKIP_FETCH_OBJECT)) { - promisor_remote_get_direct(r, real, 1); - already_retried = 1; - continue; - } - - if (flags & OBJECT_INFO_DIE_IF_CORRUPT) { - const struct packed_git *p; - if ((flags & OBJECT_INFO_LOOKUP_REPLACE) && !oideq(real, oid)) - die(_("replacement %s not found for %s"), - oid_to_hex(real), oid_to_hex(oid)); - if ((p = has_packed_and_bad(r, real))) - die(_("packed object %s (stored in %s) is corrupt"), - oid_to_hex(real), p->pack_name); - } - return -1; - } - - if (oi == &blank_oi) - /* - * We know that the caller doesn't actually need the - * information below, so return early. - */ - return 0; - rtype = packed_object_info(r, e.p, e.offset, oi); - if (rtype < 0) { - mark_bad_packed_object(e.p, real); - return do_oid_object_info_extended(r, real, oi, 0); - } else if (oi->whence == OI_PACKED) { - oi->u.packed.offset = e.offset; - oi->u.packed.pack = e.p; - oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA || - rtype == OBJ_OFS_DELTA); - } - - return 0; -} - -static int oid_object_info_convert(struct repository *r, - const struct object_id *input_oid, - struct object_info *input_oi, unsigned flags) -{ - const struct git_hash_algo *input_algo = &hash_algos[input_oid->algo]; - int do_die = flags & OBJECT_INFO_DIE_IF_CORRUPT; - struct strbuf type_name = STRBUF_INIT; - struct object_id oid, delta_base_oid; - struct object_info new_oi, *oi; - unsigned long size; - void *content; - int ret; - - if (repo_oid_to_algop(r, input_oid, the_hash_algo, &oid)) { - if (do_die) - die(_("missing mapping of %s to %s"), - oid_to_hex(input_oid), the_hash_algo->name); - return -1; - } - - /* Is new_oi needed? */ - oi = input_oi; - if (input_oi && (input_oi->delta_base_oid || input_oi->sizep || - input_oi->contentp)) { - new_oi = *input_oi; - /* Does delta_base_oid need to be converted? */ - if (input_oi->delta_base_oid) - new_oi.delta_base_oid = &delta_base_oid; - /* Will the attributes differ when converted? */ - if (input_oi->sizep || input_oi->contentp) { - new_oi.contentp = &content; - new_oi.sizep = &size; - new_oi.type_name = &type_name; - } - oi = &new_oi; - } - - ret = oid_object_info_extended(r, &oid, oi, flags); - if (ret) - return -1; - if (oi == input_oi) - return ret; - - if (new_oi.contentp) { - struct strbuf outbuf = STRBUF_INIT; - enum object_type type; - - type = type_from_string_gently(type_name.buf, type_name.len, - !do_die); - if (type == -1) - return -1; - if (type != OBJ_BLOB) { - ret = convert_object_file(&outbuf, - the_hash_algo, input_algo, - content, size, type, !do_die); - free(content); - if (ret == -1) - return -1; - size = outbuf.len; - content = strbuf_detach(&outbuf, NULL); - } - if (input_oi->sizep) - *input_oi->sizep = size; - if (input_oi->contentp) - *input_oi->contentp = content; - else - free(content); - if (input_oi->type_name) - *input_oi->type_name = type_name; - else - strbuf_release(&type_name); - } - if (new_oi.delta_base_oid == &delta_base_oid) { - if (repo_oid_to_algop(r, &delta_base_oid, input_algo, - input_oi->delta_base_oid)) { - if (do_die) - die(_("missing mapping of %s to %s"), - oid_to_hex(&delta_base_oid), - input_algo->name); - return -1; - } - } - input_oi->whence = new_oi.whence; - input_oi->u = new_oi.u; - return ret; -} - -int oid_object_info_extended(struct repository *r, const struct object_id *oid, - struct object_info *oi, unsigned flags) -{ - int ret; - - if (oid->algo && (hash_algo_by_ptr(r->hash_algo) != oid->algo)) - return oid_object_info_convert(r, oid, oi, flags); - - obj_read_lock(); - ret = do_oid_object_info_extended(r, oid, oi, flags); - obj_read_unlock(); - return ret; -} - - -/* returns enum object_type or negative */ -int oid_object_info(struct repository *r, - const struct object_id *oid, - unsigned long *sizep) -{ - enum object_type type; - struct object_info oi = OBJECT_INFO_INIT; - - oi.typep = &type; - oi.sizep = sizep; - if (oid_object_info_extended(r, oid, &oi, - OBJECT_INFO_LOOKUP_REPLACE) < 0) - return -1; - return type; -} - -int pretend_object_file(void *buf, unsigned long len, enum object_type type, - struct object_id *oid) -{ - struct cached_object_entry *co; - char *co_buf; - - hash_object_file(the_hash_algo, buf, len, type, oid); - if (repo_has_object_file_with_flags(the_repository, oid, OBJECT_INFO_QUICK | OBJECT_INFO_SKIP_FETCH_OBJECT) || - find_cached_object(oid)) - return 0; - ALLOC_GROW(cached_objects, cached_object_nr + 1, cached_object_alloc); - co = &cached_objects[cached_object_nr++]; - co->value.size = len; - co->value.type = type; - co_buf = xmalloc(len); - memcpy(co_buf, buf, len); - co->value.buf = co_buf; - oidcpy(&co->oid, oid); - return 0; -} - -/* - * This function dies on corrupt objects; the callers who want to - * deal with them should arrange to call oid_object_info_extended() and give - * error messages themselves. - */ -void *repo_read_object_file(struct repository *r, - const struct object_id *oid, - enum object_type *type, - unsigned long *size) -{ - struct object_info oi = OBJECT_INFO_INIT; - unsigned flags = OBJECT_INFO_DIE_IF_CORRUPT | OBJECT_INFO_LOOKUP_REPLACE; - void *data; - - oi.typep = type; - oi.sizep = size; - oi.contentp = &data; - if (oid_object_info_extended(r, oid, &oi, flags)) - return NULL; - - return data; -} - -void *read_object_with_reference(struct repository *r, - const struct object_id *oid, - enum object_type required_type, - unsigned long *size, - struct object_id *actual_oid_return) -{ - enum object_type type; - void *buffer; - unsigned long isize; - struct object_id actual_oid; - - oidcpy(&actual_oid, oid); - while (1) { - int ref_length = -1; - const char *ref_type = NULL; - - buffer = repo_read_object_file(r, &actual_oid, &type, &isize); - if (!buffer) - return NULL; - if (type == required_type) { - *size = isize; - if (actual_oid_return) - oidcpy(actual_oid_return, &actual_oid); - return buffer; - } - /* Handle references */ - else if (type == OBJ_COMMIT) - ref_type = "tree "; - else if (type == OBJ_TAG) - ref_type = "object "; - else { - free(buffer); - return NULL; - } - ref_length = strlen(ref_type); - - if (ref_length + the_hash_algo->hexsz > isize || - memcmp(buffer, ref_type, ref_length) || - get_oid_hex((char *) buffer + ref_length, &actual_oid)) { - free(buffer); - return NULL; - } - free(buffer); - /* Now we have the ID of the referred-to object in - * actual_oid. Check again. */ - } -} - -static void hash_object_body(const struct git_hash_algo *algo, git_hash_ctx *c, +static void hash_object_body(const struct git_hash_algo *algo, struct git_hash_ctx *c, const void *buf, unsigned long len, struct object_id *oid, char *hdr, int *hdrlen) { algo->init_fn(c); - algo->update_fn(c, hdr, *hdrlen); - algo->update_fn(c, buf, len); - algo->final_oid_fn(oid, c); + git_hash_update(c, hdr, *hdrlen); + git_hash_update(c, buf, len); + git_hash_final_oid(oid, c); } static void write_object_file_prepare(const struct git_hash_algo *algo, @@ -1950,7 +516,7 @@ static void write_object_file_prepare(const struct git_hash_algo *algo, enum object_type type, struct object_id *oid, char *hdr, int *hdrlen) { - git_hash_ctx c; + struct git_hash_ctx c; /* Generate the header */ *hdrlen = format_object_header(hdr, *hdrlen, type, len); @@ -1959,81 +525,80 @@ static void write_object_file_prepare(const struct git_hash_algo *algo, hash_object_body(algo, &c, buf, len, oid, hdr, hdrlen); } -static void write_object_file_prepare_literally(const struct git_hash_algo *algo, - const void *buf, unsigned long len, - const char *type, struct object_id *oid, - char *hdr, int *hdrlen) -{ - git_hash_ctx c; - - *hdrlen = format_object_header_literally(hdr, *hdrlen, type, len); - hash_object_body(algo, &c, buf, len, oid, hdr, hdrlen); -} +#define CHECK_COLLISION_DEST_VANISHED -2 -static int check_collision(const char *filename_a, const char *filename_b) +static int check_collision(const char *source, const char *dest) { - char buf_a[4096], buf_b[4096]; - int fd_a = -1, fd_b = -1; + char buf_source[4096], buf_dest[4096]; + int fd_source = -1, fd_dest = -1; int ret = 0; - fd_a = open(filename_a, O_RDONLY); - if (fd_a < 0) { - ret = error_errno(_("unable to open %s"), filename_a); + fd_source = open(source, O_RDONLY); + if (fd_source < 0) { + ret = error_errno(_("unable to open %s"), source); goto out; } - fd_b = open(filename_b, O_RDONLY); - if (fd_b < 0) { - ret = error_errno(_("unable to open %s"), filename_b); + fd_dest = open(dest, O_RDONLY); + if (fd_dest < 0) { + if (errno != ENOENT) + ret = error_errno(_("unable to open %s"), dest); + else + ret = CHECK_COLLISION_DEST_VANISHED; goto out; } while (1) { ssize_t sz_a, sz_b; - sz_a = read_in_full(fd_a, buf_a, sizeof(buf_a)); + sz_a = read_in_full(fd_source, buf_source, sizeof(buf_source)); if (sz_a < 0) { - ret = error_errno(_("unable to read %s"), filename_a); + ret = error_errno(_("unable to read %s"), source); goto out; } - sz_b = read_in_full(fd_b, buf_b, sizeof(buf_b)); + sz_b = read_in_full(fd_dest, buf_dest, sizeof(buf_dest)); if (sz_b < 0) { - ret = error_errno(_("unable to read %s"), filename_b); + ret = error_errno(_("unable to read %s"), dest); goto out; } - if (sz_a != sz_b || memcmp(buf_a, buf_b, sz_a)) { + if (sz_a != sz_b || memcmp(buf_source, buf_dest, sz_a)) { ret = error(_("files '%s' and '%s' differ in contents"), - filename_a, filename_b); + source, dest); goto out; } - if (sz_a < sizeof(buf_a)) + if ((size_t) sz_a < sizeof(buf_source)) break; } out: - if (fd_a > -1) - close(fd_a); - if (fd_b > -1) - close(fd_b); + if (fd_source > -1) + close(fd_source); + if (fd_dest > -1) + close(fd_dest); return ret; } /* * Move the just written object into its final resting place. */ -int finalize_object_file(const char *tmpfile, const char *filename) +int finalize_object_file(struct repository *repo, + const char *tmpfile, const char *filename) { - return finalize_object_file_flags(tmpfile, filename, 0); + return finalize_object_file_flags(repo, tmpfile, filename, 0); } -int finalize_object_file_flags(const char *tmpfile, const char *filename, +int finalize_object_file_flags(struct repository *repo, + const char *tmpfile, const char *filename, enum finalize_object_file_flags flags) { - struct stat st; - int ret = 0; + unsigned retries = 0; + int ret; + +retry: + ret = 0; if (object_creation_mode == OBJECT_CREATION_USES_RENAMES) goto try_rename; @@ -2054,6 +619,8 @@ int finalize_object_file_flags(const char *tmpfile, const char *filename, * left to unlink. */ if (ret && ret != EEXIST) { + struct stat st; + try_rename: if (!stat(filename, &st)) ret = EEXIST; @@ -2069,39 +636,41 @@ int finalize_object_file_flags(const char *tmpfile, const char *filename, errno = saved_errno; return error_errno(_("unable to write file %s"), filename); } - if (!(flags & FOF_SKIP_COLLISION_CHECK) && - check_collision(tmpfile, filename)) + if (!(flags & FOF_SKIP_COLLISION_CHECK)) { + ret = check_collision(tmpfile, filename); + if (ret == CHECK_COLLISION_DEST_VANISHED) { + if (retries++ > 5) + return error(_("unable to write repeatedly vanishing file %s"), + filename); + goto retry; + } + else if (ret) return -1; + } unlink_or_warn(tmpfile); } out: - if (adjust_shared_perm(filename)) + if (adjust_shared_perm(repo, filename)) return error(_("unable to set permission to '%s'"), filename); return 0; } -static void hash_object_file_literally(const struct git_hash_algo *algo, - const void *buf, unsigned long len, - const char *type, struct object_id *oid) -{ - char hdr[MAX_HEADER_LEN]; - int hdrlen = sizeof(hdr); - - write_object_file_prepare_literally(algo, buf, len, type, oid, hdr, &hdrlen); -} - void hash_object_file(const struct git_hash_algo *algo, const void *buf, unsigned long len, enum object_type type, struct object_id *oid) { - hash_object_file_literally(algo, buf, len, type_name(type), oid); + char hdr[MAX_HEADER_LEN]; + int hdrlen = sizeof(hdr); + + write_object_file_prepare(algo, buf, len, type, oid, hdr, &hdrlen); } /* Finalize a file on disk, and close it. */ -static void close_loose_object(int fd, const char *filename) +static void close_loose_object(struct odb_source *source, + int fd, const char *filename) { - if (the_repository->objects->odb->will_destroy) + if (source->will_destroy) goto out; if (batch_fsync_enabled(FSYNC_COMPONENT_LOOSE_OBJECT)) @@ -2133,7 +702,8 @@ static inline int directory_size(const char *filename) * We want to avoid cross-directory filename renames, because those * can have problems on various filesystems (FAT, NFS, Coda). */ -static int create_tmpfile(struct strbuf *tmp, const char *filename) +static int create_tmpfile(struct repository *repo, + struct strbuf *tmp, const char *filename) { int fd, dirlen = directory_size(filename); @@ -2152,7 +722,7 @@ static int create_tmpfile(struct strbuf *tmp, const char *filename) strbuf_add(tmp, filename, dirlen - 1); if (mkdir(tmp->buf, 0777) && errno != EEXIST) return -1; - if (adjust_shared_perm(tmp->buf)) + if (adjust_shared_perm(repo, tmp->buf)) return -1; /* Try again */ @@ -2173,26 +743,26 @@ static int create_tmpfile(struct strbuf *tmp, const char *filename) * Returns a "fd", which should later be provided to * end_loose_object_common(). */ -static int start_loose_object_common(struct strbuf *tmp_file, +static int start_loose_object_common(struct odb_source *source, + struct strbuf *tmp_file, const char *filename, unsigned flags, git_zstream *stream, unsigned char *buf, size_t buflen, - git_hash_ctx *c, git_hash_ctx *compat_c, + struct git_hash_ctx *c, struct git_hash_ctx *compat_c, char *hdr, int hdrlen) { - struct repository *repo = the_repository; - const struct git_hash_algo *algo = repo->hash_algo; - const struct git_hash_algo *compat = repo->compat_hash_algo; + const struct git_hash_algo *algo = source->odb->repo->hash_algo; + const struct git_hash_algo *compat = source->odb->repo->compat_hash_algo; int fd; - fd = create_tmpfile(tmp_file, filename); + fd = create_tmpfile(source->odb->repo, tmp_file, filename); if (fd < 0) { - if (flags & HASH_SILENT) + if (flags & WRITE_OBJECT_SILENT) return -1; else if (errno == EACCES) return error(_("insufficient permission for adding " "an object to repository database %s"), - repo_get_object_directory(the_repository)); + source->path); else return error_errno( _("unable to create temporary file")); @@ -2211,9 +781,9 @@ static int start_loose_object_common(struct strbuf *tmp_file, stream->avail_in = hdrlen; while (git_deflate(stream, 0) == Z_OK) ; /* nothing */ - algo->update_fn(c, hdr, hdrlen); + git_hash_update(c, hdr, hdrlen); if (compat && compat_c) - compat->update_fn(compat_c, hdr, hdrlen); + git_hash_update(compat_c, hdr, hdrlen); return fd; } @@ -2222,21 +792,20 @@ static int start_loose_object_common(struct strbuf *tmp_file, * Common steps for the inner git_deflate() loop for writing loose * objects. Returns what git_deflate() returns. */ -static int write_loose_object_common(git_hash_ctx *c, git_hash_ctx *compat_c, +static int write_loose_object_common(struct odb_source *source, + struct git_hash_ctx *c, struct git_hash_ctx *compat_c, git_zstream *stream, const int flush, unsigned char *in0, const int fd, unsigned char *compressed, const size_t compressed_len) { - struct repository *repo = the_repository; - const struct git_hash_algo *algo = repo->hash_algo; - const struct git_hash_algo *compat = repo->compat_hash_algo; + const struct git_hash_algo *compat = source->odb->repo->compat_hash_algo; int ret; ret = git_deflate(stream, flush ? Z_FINISH : 0); - algo->update_fn(c, in0, stream->next_in - in0); + git_hash_update(c, in0, stream->next_in - in0); if (compat && compat_c) - compat->update_fn(compat_c, in0, stream->next_in - in0); + git_hash_update(compat_c, in0, stream->next_in - in0); if (write_in_full(fd, compressed, stream->next_out - compressed) < 0) die_errno(_("unable to write loose object file")); stream->next_out = compressed; @@ -2251,33 +820,33 @@ static int write_loose_object_common(git_hash_ctx *c, git_hash_ctx *compat_c, * - End the compression of zlib stream. * - Get the calculated oid to "oid". */ -static int end_loose_object_common(git_hash_ctx *c, git_hash_ctx *compat_c, +static int end_loose_object_common(struct odb_source *source, + struct git_hash_ctx *c, struct git_hash_ctx *compat_c, git_zstream *stream, struct object_id *oid, struct object_id *compat_oid) { - struct repository *repo = the_repository; - const struct git_hash_algo *algo = repo->hash_algo; - const struct git_hash_algo *compat = repo->compat_hash_algo; + const struct git_hash_algo *compat = source->odb->repo->compat_hash_algo; int ret; ret = git_deflate_end_gently(stream); if (ret != Z_OK) return ret; - algo->final_oid_fn(oid, c); + git_hash_final_oid(oid, c); if (compat && compat_c) - compat->final_oid_fn(compat_oid, compat_c); + git_hash_final_oid(compat_oid, compat_c); return Z_OK; } -static int write_loose_object(const struct object_id *oid, char *hdr, +static int write_loose_object(struct odb_source *source, + const struct object_id *oid, char *hdr, int hdrlen, const void *buf, unsigned long len, time_t mtime, unsigned flags) { int fd, ret; unsigned char compressed[4096]; git_zstream stream; - git_hash_ctx c; + struct git_hash_ctx c; struct object_id parano_oid; static struct strbuf tmp_file = STRBUF_INIT; static struct strbuf filename = STRBUF_INIT; @@ -2285,9 +854,9 @@ static int write_loose_object(const struct object_id *oid, char *hdr, if (batch_fsync_enabled(FSYNC_COMPONENT_LOOSE_OBJECT)) prepare_loose_object_bulk_checkin(); - loose_object_path(the_repository, &filename, oid); + odb_loose_path(source, &filename, oid); - fd = start_loose_object_common(&tmp_file, filename.buf, flags, + fd = start_loose_object_common(source, &tmp_file, filename.buf, flags, &stream, compressed, sizeof(compressed), &c, NULL, hdr, hdrlen); if (fd < 0) @@ -2299,14 +868,14 @@ static int write_loose_object(const struct object_id *oid, char *hdr, do { unsigned char *in0 = stream.next_in; - ret = write_loose_object_common(&c, NULL, &stream, 1, in0, fd, + ret = write_loose_object_common(source, &c, NULL, &stream, 1, in0, fd, compressed, sizeof(compressed)); } while (ret == Z_OK); if (ret != Z_STREAM_END) die(_("unable to deflate new object %s (%d)"), oid_to_hex(oid), ret); - ret = end_loose_object_common(&c, NULL, &stream, ¶no_oid, NULL); + ret = end_loose_object_common(source, &c, NULL, &stream, ¶no_oid, NULL); if (ret != Z_OK) die(_("deflateEnd on object %s failed (%d)"), oid_to_hex(oid), ret); @@ -2314,30 +883,36 @@ static int write_loose_object(const struct object_id *oid, char *hdr, die(_("confused by unstable object source data for %s"), oid_to_hex(oid)); - close_loose_object(fd, tmp_file.buf); + close_loose_object(source, fd, tmp_file.buf); if (mtime) { struct utimbuf utb; utb.actime = mtime; utb.modtime = mtime; if (utime(tmp_file.buf, &utb) < 0 && - !(flags & HASH_SILENT)) + !(flags & WRITE_OBJECT_SILENT)) warning_errno(_("failed utime() on %s"), tmp_file.buf); } - return finalize_object_file_flags(tmp_file.buf, filename.buf, + return finalize_object_file_flags(source->odb->repo, tmp_file.buf, filename.buf, FOF_SKIP_COLLISION_CHECK); } -static int freshen_loose_object(const struct object_id *oid) +static int freshen_loose_object(struct object_database *odb, + const struct object_id *oid) { - return check_and_freshen(oid, 1); + odb_prepare_alternates(odb); + for (struct odb_source *source = odb->sources; source; source = source->next) + if (check_and_freshen_source(source, oid, 1)) + return 1; + return 0; } -static int freshen_packed_object(const struct object_id *oid) +static int freshen_packed_object(struct object_database *odb, + const struct object_id *oid) { struct pack_entry e; - if (!find_pack_entry(the_repository, oid, &e)) + if (!find_pack_entry(odb->repo, oid, &e)) return 0; if (e.p->is_cruft) return 0; @@ -2349,15 +924,16 @@ static int freshen_packed_object(const struct object_id *oid) return 1; } -int stream_loose_object(struct input_stream *in_stream, size_t len, +int stream_loose_object(struct odb_source *source, + struct input_stream *in_stream, size_t len, struct object_id *oid) { - const struct git_hash_algo *compat = the_repository->compat_hash_algo; + const struct git_hash_algo *compat = source->odb->repo->compat_hash_algo; struct object_id compat_oid; int fd, ret, err = 0, flush = 0; unsigned char compressed[4096]; git_zstream stream; - git_hash_ctx c, compat_c; + struct git_hash_ctx c, compat_c; struct strbuf tmp_file = STRBUF_INIT; struct strbuf filename = STRBUF_INIT; int dirlen; @@ -2368,7 +944,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, prepare_loose_object_bulk_checkin(); /* Since oid is not determined, save tmp file to odb path. */ - strbuf_addf(&filename, "%s/", repo_get_object_directory(the_repository)); + strbuf_addf(&filename, "%s/", source->path); hdrlen = format_object_header(hdr, sizeof(hdr), OBJ_BLOB, len); /* @@ -2379,7 +955,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, * - Setup zlib stream for compression. * - Start to feed header to zlib stream. */ - fd = start_loose_object_common(&tmp_file, filename.buf, 0, + fd = start_loose_object_common(source, &tmp_file, filename.buf, 0, &stream, compressed, sizeof(compressed), &c, &compat_c, hdr, hdrlen); if (fd < 0) { @@ -2399,7 +975,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, if (in_stream->is_finished) flush = 1; } - ret = write_loose_object_common(&c, &compat_c, &stream, flush, in0, fd, + ret = write_loose_object_common(source, &c, &compat_c, &stream, flush, in0, fd, compressed, sizeof(compressed)); /* * Unlike write_loose_object(), we do not have the entire @@ -2422,17 +998,18 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, */ if (ret != Z_STREAM_END) die(_("unable to stream deflate new object (%d)"), ret); - ret = end_loose_object_common(&c, &compat_c, &stream, oid, &compat_oid); + ret = end_loose_object_common(source, &c, &compat_c, &stream, oid, &compat_oid); if (ret != Z_OK) die(_("deflateEnd on stream object failed (%d)"), ret); - close_loose_object(fd, tmp_file.buf); + close_loose_object(source, fd, tmp_file.buf); - if (freshen_packed_object(oid) || freshen_loose_object(oid)) { + if (freshen_packed_object(source->odb, oid) || + freshen_loose_object(source->odb, oid)) { unlink_or_warn(tmp_file.buf); goto cleanup; } - loose_object_path(the_repository, &filename, oid); + odb_loose_path(source, &filename, oid); /* We finally know the object path, and create the missing dir. */ dirlen = directory_size(filename.buf); @@ -2440,7 +1017,8 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, struct strbuf dir = STRBUF_INIT; strbuf_add(&dir, filename.buf, dirlen); - if (mkdir_in_gitdir(dir.buf) && errno != EEXIST) { + if (safe_create_dir_in_gitdir(source->odb->repo, dir.buf) && + errno != EEXIST) { err = error_errno(_("unable to create directory %s"), dir.buf); strbuf_release(&dir); goto cleanup; @@ -2448,23 +1026,23 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, strbuf_release(&dir); } - err = finalize_object_file_flags(tmp_file.buf, filename.buf, + err = finalize_object_file_flags(source->odb->repo, tmp_file.buf, filename.buf, FOF_SKIP_COLLISION_CHECK); if (!err && compat) - err = repo_add_loose_object_map(the_repository, oid, &compat_oid); + err = repo_add_loose_object_map(source, oid, &compat_oid); cleanup: strbuf_release(&tmp_file); strbuf_release(&filename); return err; } -int write_object_file_flags(const void *buf, unsigned long len, - enum object_type type, struct object_id *oid, - struct object_id *compat_oid_in, unsigned flags) +int write_object_file(struct odb_source *source, + const void *buf, unsigned long len, + enum object_type type, struct object_id *oid, + struct object_id *compat_oid_in, unsigned flags) { - struct repository *repo = the_repository; - const struct git_hash_algo *algo = repo->hash_algo; - const struct git_hash_algo *compat = repo->compat_hash_algo; + const struct git_hash_algo *algo = source->odb->repo->hash_algo; + const struct git_hash_algo *compat = source->odb->repo->compat_hash_algo; struct object_id compat_oid; char hdr[MAX_HEADER_LEN]; int hdrlen = sizeof(hdr); @@ -2477,7 +1055,7 @@ int write_object_file_flags(const void *buf, unsigned long len, hash_object_file(compat, buf, len, type, &compat_oid); else { struct strbuf converted = STRBUF_INIT; - convert_object_file(&converted, algo, compat, + convert_object_file(source->odb->repo, &converted, algo, compat, buf, len, type, 0); hash_object_file(compat, converted.buf, converted.len, type, &compat_oid); @@ -2489,65 +1067,20 @@ int write_object_file_flags(const void *buf, unsigned long len, * it out into .git/objects/??/?{38} file. */ write_object_file_prepare(algo, buf, len, type, oid, hdr, &hdrlen); - if (freshen_packed_object(oid) || freshen_loose_object(oid)) + if (freshen_packed_object(source->odb, oid) || + freshen_loose_object(source->odb, oid)) return 0; - if (write_loose_object(oid, hdr, hdrlen, buf, len, 0, flags)) + if (write_loose_object(source, oid, hdr, hdrlen, buf, len, 0, flags)) return -1; if (compat) - return repo_add_loose_object_map(repo, oid, &compat_oid); + return repo_add_loose_object_map(source, oid, &compat_oid); return 0; } -int write_object_file_literally(const void *buf, unsigned long len, - const char *type, struct object_id *oid, - unsigned flags) +int force_object_loose(struct odb_source *source, + const struct object_id *oid, time_t mtime) { - char *header; - struct repository *repo = the_repository; - const struct git_hash_algo *algo = repo->hash_algo; - const struct git_hash_algo *compat = repo->compat_hash_algo; - struct object_id compat_oid; - int hdrlen, status = 0; - int compat_type = -1; - - if (compat) { - compat_type = type_from_string_gently(type, -1, 1); - if (compat_type == OBJ_BLOB) - hash_object_file(compat, buf, len, compat_type, - &compat_oid); - else if (compat_type != -1) { - struct strbuf converted = STRBUF_INIT; - convert_object_file(&converted, algo, compat, - buf, len, compat_type, 0); - hash_object_file(compat, converted.buf, converted.len, - compat_type, &compat_oid); - strbuf_release(&converted); - } - } - - /* type string, SP, %lu of the length plus NUL must fit this */ - hdrlen = strlen(type) + MAX_HEADER_LEN; - header = xmalloc(hdrlen); - write_object_file_prepare_literally(the_hash_algo, buf, len, type, - oid, header, &hdrlen); - - if (!(flags & HASH_WRITE_OBJECT)) - goto cleanup; - if (freshen_packed_object(oid) || freshen_loose_object(oid)) - goto cleanup; - status = write_loose_object(oid, header, hdrlen, buf, len, 0, 0); - if (compat_type != -1) - return repo_add_loose_object_map(repo, oid, &compat_oid); - -cleanup: - free(header); - return status; -} - -int force_object_loose(const struct object_id *oid, time_t mtime) -{ - struct repository *repo = the_repository; - const struct git_hash_algo *compat = repo->compat_hash_algo; + const struct git_hash_algo *compat = source->odb->repo->compat_hash_algo; void *buf; unsigned long len; struct object_info oi = OBJECT_INFO_INIT; @@ -2557,53 +1090,29 @@ int force_object_loose(const struct object_id *oid, time_t mtime) int hdrlen; int ret; - if (has_loose_object(oid)) - return 0; + for (struct odb_source *s = source->odb->sources; s; s = s->next) + if (has_loose_object(s, oid)) + return 0; + oi.typep = &type; oi.sizep = &len; oi.contentp = &buf; - if (oid_object_info_extended(the_repository, oid, &oi, 0)) + if (odb_read_object_info_extended(source->odb, oid, &oi, 0)) return error(_("cannot read object for %s"), oid_to_hex(oid)); if (compat) { - if (repo_oid_to_algop(repo, oid, compat, &compat_oid)) + if (repo_oid_to_algop(source->odb->repo, oid, compat, &compat_oid)) return error(_("cannot map object %s to %s"), oid_to_hex(oid), compat->name); } hdrlen = format_object_header(hdr, sizeof(hdr), type, len); - ret = write_loose_object(oid, hdr, hdrlen, buf, len, mtime, 0); + ret = write_loose_object(source, oid, hdr, hdrlen, buf, len, mtime, 0); if (!ret && compat) - ret = repo_add_loose_object_map(the_repository, oid, &compat_oid); + ret = repo_add_loose_object_map(source, oid, &compat_oid); free(buf); return ret; } -int has_object(struct repository *r, const struct object_id *oid, - unsigned flags) -{ - int quick = !(flags & HAS_OBJECT_RECHECK_PACKED); - unsigned object_info_flags = OBJECT_INFO_SKIP_FETCH_OBJECT | - (quick ? OBJECT_INFO_QUICK : 0); - - if (!startup_info->have_repository) - return 0; - return oid_object_info_extended(r, oid, NULL, object_info_flags) >= 0; -} - -int repo_has_object_file_with_flags(struct repository *r, - const struct object_id *oid, int flags) -{ - if (!startup_info->have_repository) - return 0; - return oid_object_info_extended(r, oid, NULL, flags) >= 0; -} - -int repo_has_object_file(struct repository *r, - const struct object_id *oid) -{ - return repo_has_object_file_with_flags(r, oid, 0); -} - /* * We can't use the normal fsck_error_function() for index_mem(), * because we don't yet have a valid oid for it to report. Instead, @@ -2628,7 +1137,7 @@ static int index_mem(struct index_state *istate, { struct strbuf nbuf = STRBUF_INIT; int ret = 0; - int write_object = flags & HASH_WRITE_OBJECT; + int write_object = flags & INDEX_WRITE_OBJECT; if (!type) type = OBJ_BLOB; @@ -2643,20 +1152,20 @@ static int index_mem(struct index_state *istate, size = nbuf.len; } } - if (flags & HASH_FORMAT_CHECK) { + if (flags & INDEX_FORMAT_CHECK) { struct fsck_options opts = FSCK_OPTIONS_DEFAULT; opts.strict = 1; opts.error_func = hash_format_check_report; - if (fsck_buffer(null_oid(), type, buf, size, &opts)) + if (fsck_buffer(null_oid(istate->repo->hash_algo), type, buf, size, &opts)) die(_("refusing to create malformed object")); fsck_finish(&opts); } if (write_object) - ret = write_object_file(buf, size, type, oid); + ret = odb_write_object(istate->repo->objects, buf, size, type, oid); else - hash_object_file(the_hash_algo, buf, size, type, oid); + hash_object_file(istate->repo->hash_algo, buf, size, type, oid); strbuf_release(&nbuf); return ret; @@ -2669,20 +1178,20 @@ static int index_stream_convert_blob(struct index_state *istate, unsigned flags) { int ret = 0; - const int write_object = flags & HASH_WRITE_OBJECT; + const int write_object = flags & INDEX_WRITE_OBJECT; struct strbuf sbuf = STRBUF_INIT; assert(path); - assert(would_convert_to_git_filter_fd(istate, path)); + ASSERT(would_convert_to_git_filter_fd(istate, path)); convert_to_git_filter_fd(istate, path, fd, &sbuf, get_conv_flags(flags)); if (write_object) - ret = write_object_file(sbuf.buf, sbuf.len, OBJ_BLOB, - oid); + ret = odb_write_object(istate->repo->objects, sbuf.buf, sbuf.len, OBJ_BLOB, + oid); else - hash_object_file(the_hash_algo, sbuf.buf, sbuf.len, OBJ_BLOB, + hash_object_file(istate->repo->hash_algo, sbuf.buf, sbuf.len, OBJ_BLOB, oid); strbuf_release(&sbuf); return ret; @@ -2720,7 +1229,7 @@ static int index_core(struct index_state *istate, if (read_result < 0) ret = error_errno(_("read error while indexing %s"), path ? path : "<unknown>"); - else if (read_result != size) + else if ((size_t) read_result != size) ret = error(_("short read while indexing %s"), path ? path : "<unknown>"); else @@ -2734,28 +1243,6 @@ static int index_core(struct index_state *istate, return ret; } -/* - * This creates one packfile per large blob unless bulk-checkin - * machinery is "plugged". - * - * This also bypasses the usual "convert-to-git" dance, and that is on - * purpose. We could write a streaming version of the converting - * functions and insert that before feeding the data to fast-import - * (or equivalent in-core API described above). However, that is - * somewhat complicated, as we do not know the size of the filter - * result, which we need to know beforehand when writing a git object. - * Since the primary motivation for trying to stream from the working - * tree file and to avoid mmaping it in core is to deal with large - * binary blobs, they generally do not want to get any conversion, and - * callers should avoid this code path when filters are requested. - */ -static int index_blob_stream(struct object_id *oid, int fd, size_t size, - const char *path, - unsigned flags) -{ - return index_blob_bulk_checkin(oid, fd, size, path, flags); -} - int index_fd(struct index_state *istate, struct object_id *oid, int fd, struct stat *st, enum object_type type, const char *path, unsigned flags) @@ -2770,13 +1257,14 @@ int index_fd(struct index_state *istate, struct object_id *oid, ret = index_stream_convert_blob(istate, oid, fd, path, flags); else if (!S_ISREG(st->st_mode)) ret = index_pipe(istate, oid, fd, type, path, flags); - else if (st->st_size <= big_file_threshold || type != OBJ_BLOB || + else if ((st->st_size >= 0 && (size_t) st->st_size <= repo_settings_get_big_file_threshold(istate->repo)) || + type != OBJ_BLOB || (path && would_convert_to_git(istate, path))) ret = index_core(istate, oid, fd, xsize_t(st->st_size), type, path, flags); else - ret = index_blob_stream(oid, fd, xsize_t(st->st_size), path, - flags); + ret = index_blob_bulk_checkin(oid, fd, xsize_t(st->st_size), path, + flags); close(fd); return ret; } @@ -2800,15 +1288,15 @@ int index_path(struct index_state *istate, struct object_id *oid, case S_IFLNK: if (strbuf_readlink(&sb, path, st->st_size)) return error_errno("readlink(\"%s\")", path); - if (!(flags & HASH_WRITE_OBJECT)) - hash_object_file(the_hash_algo, sb.buf, sb.len, + if (!(flags & INDEX_WRITE_OBJECT)) + hash_object_file(istate->repo->hash_algo, sb.buf, sb.len, OBJ_BLOB, oid); - else if (write_object_file(sb.buf, sb.len, OBJ_BLOB, oid)) + else if (odb_write_object(istate->repo->objects, sb.buf, sb.len, OBJ_BLOB, oid)) rc = error(_("%s: failed to insert into database"), path); strbuf_release(&sb); break; case S_IFDIR: - return repo_resolve_gitlink_ref(the_repository, path, "HEAD", oid); + return repo_resolve_gitlink_ref(istate->repo, path, "HEAD", oid); default: return error(_("%s: unsupported file type"), path); } @@ -2830,22 +1318,13 @@ int read_pack_header(int fd, struct pack_header *header) return 0; } -void assert_oid_type(const struct object_id *oid, enum object_type expect) -{ - enum object_type type = oid_object_info(the_repository, oid, NULL); - if (type < 0) - die(_("%s is not a valid object"), oid_to_hex(oid)); - if (type != expect) - die(_("%s is not a valid '%s' object"), oid_to_hex(oid), - type_name(expect)); -} - -int for_each_file_in_obj_subdir(unsigned int subdir_nr, - struct strbuf *path, - each_loose_object_fn obj_cb, - each_loose_cruft_fn cruft_cb, - each_loose_subdir_fn subdir_cb, - void *data) +static int for_each_file_in_obj_subdir(unsigned int subdir_nr, + struct strbuf *path, + const struct git_hash_algo *algop, + each_loose_object_fn obj_cb, + each_loose_cruft_fn cruft_cb, + each_loose_subdir_fn subdir_cb, + void *data) { size_t origlen, baselen; DIR *dir; @@ -2878,12 +1357,12 @@ int for_each_file_in_obj_subdir(unsigned int subdir_nr, namelen = strlen(de->d_name); strbuf_setlen(path, baselen); strbuf_add(path, de->d_name, namelen); - if (namelen == the_hash_algo->hexsz - 2 && + if (namelen == algop->hexsz - 2 && !hex_to_bytes(oid.hash + 1, de->d_name, - the_hash_algo->rawsz - 1)) { - oid_set_algo(&oid, the_hash_algo); - memset(oid.hash + the_hash_algo->rawsz, 0, - GIT_MAX_RAWSZ - the_hash_algo->rawsz); + algop->rawsz - 1)) { + oid_set_algo(&oid, algop); + memset(oid.hash + algop->rawsz, 0, + GIT_MAX_RAWSZ - algop->rawsz); if (obj_cb) { r = obj_cb(&oid, path->buf, data); if (r) @@ -2909,26 +1388,7 @@ int for_each_file_in_obj_subdir(unsigned int subdir_nr, return r; } -int for_each_loose_file_in_objdir_buf(struct strbuf *path, - each_loose_object_fn obj_cb, - each_loose_cruft_fn cruft_cb, - each_loose_subdir_fn subdir_cb, - void *data) -{ - int r = 0; - int i; - - for (i = 0; i < 256; i++) { - r = for_each_file_in_obj_subdir(i, path, obj_cb, cruft_cb, - subdir_cb, data); - if (r) - break; - } - - return r; -} - -int for_each_loose_file_in_objdir(const char *path, +int for_each_loose_file_in_source(struct odb_source *source, each_loose_object_fn obj_cb, each_loose_cruft_fn cruft_cb, each_loose_subdir_fn subdir_cb, @@ -2937,22 +1397,27 @@ int for_each_loose_file_in_objdir(const char *path, struct strbuf buf = STRBUF_INIT; int r; - strbuf_addstr(&buf, path); - r = for_each_loose_file_in_objdir_buf(&buf, obj_cb, cruft_cb, - subdir_cb, data); - strbuf_release(&buf); + strbuf_addstr(&buf, source->path); + for (int i = 0; i < 256; i++) { + r = for_each_file_in_obj_subdir(i, &buf, source->odb->repo->hash_algo, + obj_cb, cruft_cb, subdir_cb, data); + if (r) + break; + } + strbuf_release(&buf); return r; } -int for_each_loose_object(each_loose_object_fn cb, void *data, +int for_each_loose_object(struct object_database *odb, + each_loose_object_fn cb, void *data, enum for_each_object_flags flags) { - struct object_directory *odb; + struct odb_source *source; - prepare_alt_odb(the_repository); - for (odb = the_repository->objects->odb; odb; odb = odb->next) { - int r = for_each_loose_file_in_objdir(odb->path, cb, NULL, + odb_prepare_alternates(odb); + for (source = odb->sources; source; source = source->next) { + int r = for_each_loose_file_in_source(source, cb, NULL, NULL, data); if (r) return r; @@ -2972,59 +1437,61 @@ static int append_loose_object(const struct object_id *oid, return 0; } -struct oidtree *odb_loose_cache(struct object_directory *odb, - const struct object_id *oid) +struct oidtree *odb_loose_cache(struct odb_source *source, + const struct object_id *oid) { int subdir_nr = oid->hash[0]; struct strbuf buf = STRBUF_INIT; - size_t word_bits = bitsizeof(odb->loose_objects_subdir_seen[0]); + size_t word_bits = bitsizeof(source->loose_objects_subdir_seen[0]); size_t word_index = subdir_nr / word_bits; size_t mask = (size_t)1u << (subdir_nr % word_bits); uint32_t *bitmap; if (subdir_nr < 0 || - subdir_nr >= bitsizeof(odb->loose_objects_subdir_seen)) + (size_t) subdir_nr >= bitsizeof(source->loose_objects_subdir_seen)) BUG("subdir_nr out of range"); - bitmap = &odb->loose_objects_subdir_seen[word_index]; + bitmap = &source->loose_objects_subdir_seen[word_index]; if (*bitmap & mask) - return odb->loose_objects_cache; - if (!odb->loose_objects_cache) { - ALLOC_ARRAY(odb->loose_objects_cache, 1); - oidtree_init(odb->loose_objects_cache); + return source->loose_objects_cache; + if (!source->loose_objects_cache) { + ALLOC_ARRAY(source->loose_objects_cache, 1); + oidtree_init(source->loose_objects_cache); } - strbuf_addstr(&buf, odb->path); + strbuf_addstr(&buf, source->path); for_each_file_in_obj_subdir(subdir_nr, &buf, + source->odb->repo->hash_algo, append_loose_object, NULL, NULL, - odb->loose_objects_cache); + source->loose_objects_cache); *bitmap |= mask; strbuf_release(&buf); - return odb->loose_objects_cache; + return source->loose_objects_cache; } -void odb_clear_loose_cache(struct object_directory *odb) +void odb_clear_loose_cache(struct odb_source *source) { - oidtree_clear(odb->loose_objects_cache); - FREE_AND_NULL(odb->loose_objects_cache); - memset(&odb->loose_objects_subdir_seen, 0, - sizeof(odb->loose_objects_subdir_seen)); + oidtree_clear(source->loose_objects_cache); + FREE_AND_NULL(source->loose_objects_cache); + memset(&source->loose_objects_subdir_seen, 0, + sizeof(source->loose_objects_subdir_seen)); } static int check_stream_oid(git_zstream *stream, const char *hdr, unsigned long size, const char *path, - const struct object_id *expected_oid) + const struct object_id *expected_oid, + const struct git_hash_algo *algop) { - git_hash_ctx c; + struct git_hash_ctx c; struct object_id real_oid; unsigned char buf[4096]; unsigned long total_read; int status = Z_OK; - the_hash_algo->init_fn(&c); - the_hash_algo->update_fn(&c, hdr, stream->total_out); + algop->init_fn(&c); + git_hash_update(&c, hdr, stream->total_out); /* * We already read some bytes into hdr, but the ones up to the NUL @@ -3044,10 +1511,9 @@ static int check_stream_oid(git_zstream *stream, if (size - total_read < stream->avail_out) stream->avail_out = size - total_read; status = git_inflate(stream, Z_FINISH); - the_hash_algo->update_fn(&c, buf, stream->next_out - buf); + git_hash_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'"), oid_to_hex(expected_oid)); @@ -3059,7 +1525,7 @@ static int check_stream_oid(git_zstream *stream, return -1; } - the_hash_algo->final_oid_fn(&real_oid, &c); + git_hash_final_oid(&real_oid, &c); if (!oideq(expected_oid, &real_oid)) { error(_("hash mismatch for %s (expected %s)"), path, oid_to_hex(expected_oid)); @@ -3069,7 +1535,8 @@ static int check_stream_oid(git_zstream *stream, return 0; } -int read_loose_object(const char *path, +int read_loose_object(struct repository *repo, + const char *path, const struct object_id *expected_oid, struct object_id *real_oid, void **contents, @@ -3091,38 +1558,44 @@ int read_loose_object(const char *path, goto out; } - if (unpack_loose_header(&stream, map, mapsize, hdr, sizeof(hdr), - NULL) != ULHR_OK) { + if (unpack_loose_header(&stream, map, mapsize, hdr, sizeof(hdr)) != ULHR_OK) { error(_("unable to unpack header of %s"), path); - git_inflate_end(&stream); - goto out; + goto out_inflate; } if (parse_loose_header(hdr, oi) < 0) { error(_("unable to parse header of %s"), path); - git_inflate_end(&stream); - goto out; + goto out_inflate; } - if (*oi->typep == OBJ_BLOB && *size > big_file_threshold) { - if (check_stream_oid(&stream, hdr, *size, path, expected_oid) < 0) - goto out; + if (*oi->typep < 0) { + error(_("unable to parse type from header '%s' of %s"), + hdr, path); + goto out_inflate; + } + + if (*oi->typep == OBJ_BLOB && + *size > repo_settings_get_big_file_threshold(repo)) { + if (check_stream_oid(&stream, hdr, *size, path, expected_oid, + repo->hash_algo) < 0) + goto out_inflate; } else { *contents = unpack_loose_rest(&stream, hdr, *size, expected_oid); if (!*contents) { error(_("unable to unpack contents of %s"), path); - git_inflate_end(&stream); - goto out; + goto out_inflate; } - hash_object_file_literally(the_repository->hash_algo, - *contents, *size, - oi->type_name->buf, real_oid); + hash_object_file(repo->hash_algo, + *contents, *size, + *oi->typep, real_oid); if (!oideq(expected_oid, real_oid)) - goto out; + goto out_inflate; } ret = 0; /* everything checks out */ +out_inflate: + git_inflate_end(&stream); out: if (map) munmap(map, mapsize); |