diff --git a/Makefile b/Makefile index 13f9062a05..0b46dee0da 100644 --- a/Makefile +++ b/Makefile @@ -994,6 +994,7 @@ LIB_OBJS += common-exit.o LIB_OBJS += common-init.o LIB_OBJS += compat/nonblock.o LIB_OBJS += compat/obstack.o +LIB_OBJS += compat/open.o LIB_OBJS += compat/terminal.o LIB_OBJS += compiler-tricks/not-constant.o LIB_OBJS += config.o @@ -1084,6 +1085,7 @@ LIB_OBJS += notes.o LIB_OBJS += object-file-convert.o LIB_OBJS += object-file.o LIB_OBJS += object-name.o +LIB_OBJS += object-store.o LIB_OBJS += object.o LIB_OBJS += oid-array.o LIB_OBJS += oidmap.o @@ -1811,7 +1813,6 @@ ifdef FREAD_READS_DIRECTORIES endif ifdef OPEN_RETURNS_EINTR COMPAT_CFLAGS += -DOPEN_RETURNS_EINTR - COMPAT_OBJS += compat/open.o endif ifdef NO_SYMLINK_HEAD BASIC_CFLAGS += -DNO_SYMLINK_HEAD diff --git a/apply.c b/apply.c index f274a37948..2b6f4d0af8 100644 --- a/apply.c +++ b/apply.c @@ -14,7 +14,7 @@ #include "abspath.h" #include "base85.h" #include "config.h" -#include "object-store-ll.h" +#include "object-store.h" #include "delta.h" #include "diff.h" #include "dir.h" diff --git a/archive-tar.c b/archive-tar.c index 0edf13fba7..282b48196f 100644 --- a/archive-tar.c +++ b/archive-tar.c @@ -11,7 +11,7 @@ #include "hex.h" #include "tar.h" #include "archive.h" -#include "object-store-ll.h" +#include "object-store.h" #include "strbuf.h" #include "streaming.h" #include "run-command.h" diff --git a/archive-zip.c b/archive-zip.c index 9f32730181..405da6f3d8 100644 --- a/archive-zip.c +++ b/archive-zip.c @@ -12,7 +12,7 @@ #include "hex.h" #include "streaming.h" #include "utf8.h" -#include "object-store-ll.h" +#include "object-store.h" #include "strbuf.h" #include "userdiff.h" #include "write-or-die.h" diff --git a/archive.c b/archive.c index c95e398152..014c312178 100644 --- a/archive.c +++ b/archive.c @@ -14,7 +14,7 @@ #include "pretty.h" #include "setup.h" #include "refs.h" -#include "object-store-ll.h" +#include "object-store.h" #include "commit.h" #include "tree.h" #include "tree-walk.h" diff --git a/attr.c b/attr.c index 0bd2750528..86b6109fc4 100644 --- a/attr.c +++ b/attr.c @@ -22,7 +22,7 @@ #include "read-cache-ll.h" #include "refs.h" #include "revision.h" -#include "object-store-ll.h" +#include "object-store.h" #include "setup.h" #include "thread-utils.h" #include "tree-walk.h" diff --git a/bisect.c b/bisect.c index 269a98bf97..a327468c75 100644 --- a/bisect.c +++ b/bisect.c @@ -20,7 +20,7 @@ #include "commit-slab.h" #include "commit-reach.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "path.h" #include "dir.h" diff --git a/blame.c b/blame.c index 703dab43e7..57daa45e89 100644 --- a/blame.c +++ b/blame.c @@ -3,7 +3,7 @@ #include "git-compat-util.h" #include "refs.h" -#include "object-store-ll.h" +#include "object-store.h" #include "cache-tree.h" #include "mergesort.h" #include "commit.h" @@ -277,7 +277,7 @@ static struct commit *fake_working_tree_commit(struct repository *r, convert_to_git(r->index, path, buf.buf, buf.len, &buf, 0); origin->file.ptr = buf.buf; origin->file.size = buf.len; - pretend_object_file(buf.buf, buf.len, OBJ_BLOB, &origin->blob_oid); + pretend_object_file(the_repository, buf.buf, buf.len, OBJ_BLOB, &origin->blob_oid); /* * Read the current index, replace the path entry with diff --git a/builtin/backfill.c b/builtin/backfill.c index 33e1ea2f84..aaa104bc91 100644 --- a/builtin/backfill.c +++ b/builtin/backfill.c @@ -13,7 +13,7 @@ #include "tree.h" #include "tree-walk.h" #include "object.h" -#include "object-store-ll.h" +#include "object-store.h" #include "oid-array.h" #include "oidset.h" #include "promisor-remote.h" diff --git a/builtin/blame.c b/builtin/blame.c index 9436f70aec..5bf11c2a3c 100644 --- a/builtin/blame.c +++ b/builtin/blame.c @@ -28,7 +28,7 @@ #include "line-log.h" #include "progress.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "pager.h" #include "blame.h" #include "refs.h" diff --git a/builtin/bugreport.c b/builtin/bugreport.c index 66d64bfd5a..f78c3f2aed 100644 --- a/builtin/bugreport.c +++ b/builtin/bugreport.c @@ -4,13 +4,13 @@ #include "editor.h" #include "gettext.h" #include "parse-options.h" +#include "path.h" #include "strbuf.h" #include "help.h" #include "compat/compiler.h" #include "hook.h" #include "hook-list.h" #include "diagnose.h" -#include "object-file.h" #include "setup.h" #include "version.h" @@ -141,7 +141,7 @@ int cmd_bugreport(int argc, } strbuf_addstr(&report_path, ".txt"); - switch (safe_create_leading_directories(report_path.buf)) { + switch (safe_create_leading_directories(the_repository, report_path.buf)) { case SCLD_OK: case SCLD_EXISTS: break; diff --git a/builtin/cat-file.c b/builtin/cat-file.c index ead7554a57..0e3f10a946 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -24,7 +24,7 @@ #include "pack-bitmap.h" #include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "replace-object.h" #include "promisor-remote.h" #include "mailmap.h" diff --git a/builtin/checkout.c b/builtin/checkout.c index e69ea06713..d185982f3a 100644 --- a/builtin/checkout.c +++ b/builtin/checkout.c @@ -18,8 +18,9 @@ #include "lockfile.h" #include "mem-pool.h" #include "merge-ort-wrappers.h" +#include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "parse-options.h" #include "path.h" #include "preload-index.h" diff --git a/builtin/clone.c b/builtin/clone.c index 7d5b64a6a0..6b1d11a3ed 100644 --- a/builtin/clone.c +++ b/builtin/clone.c @@ -25,7 +25,7 @@ #include "refs.h" #include "refspec.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "tree.h" #include "tree-walk.h" #include "unpack-trees.h" @@ -1092,7 +1092,7 @@ int cmd_clone(int argc, sigchain_push_common(remove_junk_on_signal); if (!option_bare) { - if (safe_create_leading_directories_const(work_tree) < 0) + if (safe_create_leading_directories_const(the_repository, work_tree) < 0) die_errno(_("could not create leading directories of '%s'"), work_tree); if (dest_exists) @@ -1113,7 +1113,7 @@ int cmd_clone(int argc, junk_git_dir_flags |= REMOVE_DIR_KEEP_TOPLEVEL; junk_git_dir = git_dir; } - if (safe_create_leading_directories_const(git_dir) < 0) + if (safe_create_leading_directories_const(the_repository, git_dir) < 0) die(_("could not create leading directories of '%s'"), git_dir); if (0 <= option_verbosity) { diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c index 8ca75262c5..be06d0a811 100644 --- a/builtin/commit-graph.c +++ b/builtin/commit-graph.c @@ -6,7 +6,7 @@ #include "hex.h" #include "parse-options.h" #include "commit-graph.h" -#include "object-store-ll.h" +#include "object-store.h" #include "progress.h" #include "replace-object.h" #include "strbuf.h" diff --git a/builtin/commit-tree.c b/builtin/commit-tree.c index 38457600a4..6f9975e7a8 100644 --- a/builtin/commit-tree.c +++ b/builtin/commit-tree.c @@ -9,7 +9,7 @@ #include "gettext.h" #include "hex.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "commit.h" #include "parse-options.h" diff --git a/builtin/count-objects.c b/builtin/count-objects.c index 1e89148ed7..0bb5360b2f 100644 --- a/builtin/count-objects.c +++ b/builtin/count-objects.c @@ -12,7 +12,7 @@ #include "parse-options.h" #include "quote.h" #include "packfile.h" -#include "object-store-ll.h" +#include "object-store.h" static unsigned long garbage; static off_t size_garbage; diff --git a/builtin/credential-cache--daemon.c b/builtin/credential-cache--daemon.c index e707618e74..5065ff4660 100644 --- a/builtin/credential-cache--daemon.c +++ b/builtin/credential-cache--daemon.c @@ -2,8 +2,8 @@ #include "builtin.h" #include "abspath.h" #include "gettext.h" -#include "object-file.h" #include "parse-options.h" +#include "path.h" #ifndef NO_UNIX_SOCKETS @@ -271,7 +271,7 @@ static void init_socket_directory(const char *path) * condition in which somebody can chdir to it, sleep, then try to open * our protected socket. */ - if (safe_create_leading_directories_const(dir) < 0) + if (safe_create_leading_directories_const(the_repository, dir) < 0) die_errno("unable to create directories for '%s'", dir); if (mkdir(dir, 0700) < 0) die_errno("unable to mkdir '%s'", dir); diff --git a/builtin/describe.c b/builtin/describe.c index 23df333fd0..0f87fbceef 100644 --- a/builtin/describe.c +++ b/builtin/describe.c @@ -19,7 +19,7 @@ #include "setup.h" #include "strvec.h" #include "run-command.h" -#include "object-store-ll.h" +#include "object-store.h" #include "list-objects.h" #include "commit-slab.h" #include "wildmatch.h" diff --git a/builtin/diagnose.c b/builtin/diagnose.c index 33c39bd598..ec86d66389 100644 --- a/builtin/diagnose.c +++ b/builtin/diagnose.c @@ -3,8 +3,8 @@ #include "builtin.h" #include "abspath.h" #include "gettext.h" -#include "object-file.h" #include "parse-options.h" +#include "path.h" #include "diagnose.h" static const char * const diagnose_usage[] = { @@ -50,7 +50,7 @@ int cmd_diagnose(int argc, strbuf_addftime(&zip_path, option_suffix, localtime_r(&now, &tm), 0, 0); strbuf_addstr(&zip_path, ".zip"); - switch (safe_create_leading_directories(zip_path.buf)) { + switch (safe_create_leading_directories(the_repository, zip_path.buf)) { case SCLD_OK: case SCLD_EXISTS: break; diff --git a/builtin/difftool.c b/builtin/difftool.c index 41cd00066c..f17a55b3cf 100644 --- a/builtin/difftool.c +++ b/builtin/difftool.c @@ -22,6 +22,7 @@ #include "gettext.h" #include "hex.h" #include "parse-options.h" +#include "path.h" #include "read-cache-ll.h" #include "repository.h" #include "sparse-index.h" @@ -29,7 +30,7 @@ #include "strbuf.h" #include "lockfile.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "dir.h" #include "entry.h" #include "setup.h" @@ -271,9 +272,9 @@ static void changed_files(struct repository *repo, strbuf_release(&buf); } -static int ensure_leading_directories(char *path) +static int ensure_leading_directories(struct repository *repo, char *path) { - switch (safe_create_leading_directories(path)) { + switch (safe_create_leading_directories(repo, path)) { case SCLD_OK: case SCLD_EXISTS: return 0; @@ -341,11 +342,12 @@ static int checkout_path(unsigned mode, struct object_id *oid, return ret; } -static void write_file_in_directory(struct strbuf *dir, size_t dir_len, - const char *path, const char *content) +static void write_file_in_directory(struct repository *repo, + struct strbuf *dir, size_t dir_len, + const char *path, const char *content) { add_path(dir, dir_len, path); - ensure_leading_directories(dir->buf); + ensure_leading_directories(repo, dir->buf); unlink(dir->buf); write_file(dir->buf, "%s", content); } @@ -356,14 +358,15 @@ static void write_file_in_directory(struct strbuf *dir, size_t dir_len, * as text files, resulting in behavior that is analogous to what "git diff" * displays for symlink and submodule diffs. */ -static void write_standin_files(struct pair_entry *entry, - struct strbuf *ldir, size_t ldir_len, - struct strbuf *rdir, size_t rdir_len) +static void write_standin_files(struct repository *repo, + struct pair_entry *entry, + struct strbuf *ldir, size_t ldir_len, + struct strbuf *rdir, size_t rdir_len) { if (*entry->left) - write_file_in_directory(ldir, ldir_len, entry->path, entry->left); + write_file_in_directory(repo, ldir, ldir_len, entry->path, entry->left); if (*entry->right) - write_file_in_directory(rdir, rdir_len, entry->path, entry->right); + write_file_in_directory(repo, rdir, rdir_len, entry->path, entry->right); } static int run_dir_diff(struct repository *repo, @@ -533,7 +536,7 @@ static int run_dir_diff(struct repository *repo, ADD_CACHE_JUST_APPEND); add_path(&rdir, rdir_len, dst_path); - if (ensure_leading_directories(rdir.buf)) { + if (ensure_leading_directories(repo, rdir.buf)) { ret = error("could not create " "directory for '%s'", dst_path); @@ -576,7 +579,7 @@ static int run_dir_diff(struct repository *repo, */ hashmap_for_each_entry(&submodules, &iter, entry, entry /* member name */) { - write_standin_files(entry, &ldir, ldir_len, &rdir, rdir_len); + write_standin_files(repo, entry, &ldir, ldir_len, &rdir, rdir_len); } /* @@ -587,7 +590,7 @@ static int run_dir_diff(struct repository *repo, hashmap_for_each_entry(&symlinks2, &iter, entry, entry /* member name */) { - write_standin_files(entry, &ldir, ldir_len, &rdir, rdir_len); + write_standin_files(repo, entry, &ldir, ldir_len, &rdir, rdir_len); } strbuf_setlen(&ldir, ldir_len); diff --git a/builtin/fast-export.c b/builtin/fast-export.c index 170126d41a..afacd228b5 100644 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@ -14,7 +14,7 @@ #include "refs.h" #include "refspec.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "commit.h" #include "object.h" #include "tag.h" diff --git a/builtin/fast-import.c b/builtin/fast-import.c index 63880b595c..c1e198f4e3 100644 --- a/builtin/fast-import.c +++ b/builtin/fast-import.c @@ -24,7 +24,7 @@ #include "packfile.h" #include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "mem-pool.h" #include "commit-reach.h" #include "khash.h" @@ -1720,7 +1720,7 @@ static void dump_marks(void) if (!export_marks_file || (import_marks_file && !import_marks_file_done)) return; - if (safe_create_leading_directories_const(export_marks_file)) { + if (safe_create_leading_directories_const(the_repository, export_marks_file)) { failure |= error_errno("unable to create leading directories of %s", export_marks_file); return; diff --git a/builtin/fetch.c b/builtin/fetch.c index 097a98628f..95589b4994 100644 --- a/builtin/fetch.c +++ b/builtin/fetch.c @@ -14,7 +14,7 @@ #include "refs.h" #include "refspec.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "oidset.h" #include "oid-array.h" #include "commit.h" diff --git a/builtin/fsck.c b/builtin/fsck.c index 9c8a6d6a8d..6cac28356c 100644 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@ -17,7 +17,7 @@ #include "packfile.h" #include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "path.h" #include "read-cache-ll.h" #include "replace-object.h" @@ -332,7 +332,7 @@ static void check_unreachable_object(struct object *obj) describe_object(&obj->oid)); FILE *f; - if (safe_create_leading_directories_const(filename)) { + if (safe_create_leading_directories_const(the_repository, filename)) { error(_("could not create lost-found")); free(filename); return; diff --git a/builtin/gc.c b/builtin/gc.c index d5c75be252..b5ce1d3276 100644 --- a/builtin/gc.c +++ b/builtin/gc.c @@ -28,8 +28,7 @@ #include "commit.h" #include "commit-graph.h" #include "packfile.h" -#include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "pack.h" #include "pack-objects.h" #include "path.h" @@ -2169,7 +2168,7 @@ static int launchctl_schedule_plist(const char *exec_path, enum schedule_priorit } strbuf_addstr(&plist, "\n\n\n"); - if (safe_create_leading_directories(filename)) + if (safe_create_leading_directories(the_repository, filename)) die(_("failed to create directories for '%s'"), filename); if ((long)lock_file_timeout_ms < 0 && @@ -2635,7 +2634,7 @@ static int systemd_timer_write_timer_file(enum schedule_priority schedule, filename = xdg_config_home_systemd(local_timer_name); - if (safe_create_leading_directories(filename)) { + if (safe_create_leading_directories(the_repository, filename)) { error(_("failed to create directories for '%s'"), filename); goto error; } @@ -2708,7 +2707,7 @@ static int systemd_timer_write_service_template(const char *exec_path) char *local_service_name = xstrfmt(SYSTEMD_UNIT_FORMAT, "", "service"); filename = xdg_config_home_systemd(local_service_name); - if (safe_create_leading_directories(filename)) { + if (safe_create_leading_directories(the_repository, filename)) { error(_("failed to create directories for '%s'"), filename); goto error; } diff --git a/builtin/grep.c b/builtin/grep.c index 283d64cab8..bcfbe5be5b 100644 --- a/builtin/grep.c +++ b/builtin/grep.c @@ -26,7 +26,7 @@ #include "submodule-config.h" #include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "packfile.h" #include "pager.h" #include "path.h" diff --git a/builtin/hash-object.c b/builtin/hash-object.c index a25f0403f4..cd53fa3bde 100644 --- a/builtin/hash-object.c +++ b/builtin/hash-object.c @@ -11,7 +11,7 @@ #include "gettext.h" #include "hex.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "blob.h" #include "quote.h" #include "parse-options.h" @@ -19,6 +19,11 @@ #include "strbuf.h" #include "write-or-die.h" +enum { + HASH_OBJECT_CHECK = (1 << 0), + HASH_OBJECT_WRITE = (1 << 1), +}; + /* * This is to create corrupt objects for debugging and as such it * needs to bypass the data conversion performed by, and the type @@ -33,7 +38,7 @@ static int hash_literally(struct object_id *oid, int fd, const char *type, unsig ret = -1; else ret = write_object_file_literally(buf.buf, buf.len, type, oid, - flags); + (flags & HASH_OBJECT_WRITE) ? WRITE_OBJECT_FILE_PERSIST : 0); close(fd); strbuf_release(&buf); return ret; @@ -42,15 +47,21 @@ static int hash_literally(struct object_id *oid, int fd, const char *type, unsig static void hash_fd(int fd, const char *type, const char *path, unsigned flags, int literally) { + unsigned int index_flags = 0; struct stat st; struct object_id oid; + if (flags & HASH_OBJECT_WRITE) + index_flags |= INDEX_WRITE_OBJECT; + if (flags & HASH_OBJECT_CHECK) + index_flags |= INDEX_FORMAT_CHECK; + if (fstat(fd, &st) < 0 || (literally ? hash_literally(&oid, fd, type, flags) : index_fd(the_repository->index, &oid, fd, &st, - type_from_string(type), path, flags))) - die((flags & HASH_WRITE_OBJECT) + type_from_string(type), path, index_flags))) + die((flags & HASH_OBJECT_WRITE) ? "Unable to add %s to database" : "Unable to hash %s", path); printf("%s\n", oid_to_hex(&oid)); @@ -102,13 +113,13 @@ int cmd_hash_object(int argc, int no_filters = 0; int literally = 0; int nongit = 0; - unsigned flags = HASH_FORMAT_CHECK; + unsigned flags = HASH_OBJECT_CHECK; const char *vpath = NULL; char *vpath_free = NULL; const struct option hash_object_options[] = { OPT_STRING('t', NULL, &type, N_("type"), N_("object type")), OPT_BIT('w', NULL, &flags, N_("write the object into the object database"), - HASH_WRITE_OBJECT), + HASH_OBJECT_WRITE), OPT_COUNTUP( 0 , "stdin", &hashstdin, N_("read the object from stdin")), OPT_BOOL( 0 , "stdin-paths", &stdin_paths, N_("read file names from stdin")), OPT_BOOL( 0 , "no-filters", &no_filters, N_("store file as is without filters")), @@ -122,7 +133,7 @@ int cmd_hash_object(int argc, argc = parse_options(argc, argv, prefix, hash_object_options, hash_object_usage, 0); - if (flags & HASH_WRITE_OBJECT) + if (flags & HASH_OBJECT_WRITE) prefix = setup_git_directory(); else prefix = setup_git_directory_gently(&nongit); diff --git a/builtin/index-pack.c b/builtin/index-pack.c index de127c0ff1..60a8ee05db 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -21,7 +21,7 @@ #include "packfile.h" #include "pack-revindex.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "oid-array.h" #include "oidset.h" #include "path.h" diff --git a/builtin/init-db.c b/builtin/init-db.c index 196dccdd77..91c2563e34 100644 --- a/builtin/init-db.c +++ b/builtin/init-db.c @@ -8,7 +8,6 @@ #include "abspath.h" #include "environment.h" #include "gettext.h" -#include "object-file.h" #include "parse-options.h" #include "path.h" #include "refs.h" @@ -134,7 +133,7 @@ int cmd_init_db(int argc, */ saved = repo_settings_get_shared_repository(the_repository); repo_settings_set_shared_repository(the_repository, 0); - switch (safe_create_leading_directories_const(argv[0])) { + switch (safe_create_leading_directories_const(the_repository, argv[0])) { case SCLD_OK: case SCLD_PERMS: break; diff --git a/builtin/log.c b/builtin/log.c index 0d4c579dad..b450cd3bde 100644 --- a/builtin/log.c +++ b/builtin/log.c @@ -14,9 +14,8 @@ #include "gettext.h" #include "hex.h" #include "refs.h" -#include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "pager.h" #include "color.h" #include "commit.h" @@ -29,6 +28,7 @@ #include "tag.h" #include "reflog-walk.h" #include "patch-ids.h" +#include "path.h" #include "shortlog.h" #include "remote.h" #include "string-list.h" @@ -2311,7 +2311,7 @@ int cmd_format_patch(int argc, */ saved = repo_settings_get_shared_repository(the_repository); repo_settings_set_shared_repository(the_repository, 0); - switch (safe_create_leading_directories_const(output_directory)) { + switch (safe_create_leading_directories_const(the_repository, output_directory)) { case SCLD_OK: case SCLD_EXISTS: break; diff --git a/builtin/ls-tree.c b/builtin/ls-tree.c index 8542b5d53e..8aafc30ca4 100644 --- a/builtin/ls-tree.c +++ b/builtin/ls-tree.c @@ -10,7 +10,7 @@ #include "gettext.h" #include "hex.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "tree.h" #include "path.h" #include "quote.h" diff --git a/builtin/merge-file.c b/builtin/merge-file.c index 7e315f374b..2b16b10d2c 100644 --- a/builtin/merge-file.c +++ b/builtin/merge-file.c @@ -5,6 +5,7 @@ #include "abspath.h" #include "diff.h" #include "hex.h" +#include "object-file.h" #include "object-name.h" #include "object-store.h" #include "config.h" diff --git a/builtin/merge-tree.c b/builtin/merge-tree.c index 3ec7127b3a..4aafa73c61 100644 --- a/builtin/merge-tree.c +++ b/builtin/merge-tree.c @@ -10,7 +10,7 @@ #include "commit-reach.h" #include "merge-ort.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "parse-options.h" #include "blob.h" #include "merge-blobs.h" diff --git a/builtin/mktag.c b/builtin/mktag.c index 6e188dce50..7ac11c46d5 100644 --- a/builtin/mktag.c +++ b/builtin/mktag.c @@ -6,7 +6,7 @@ #include "strbuf.h" #include "replace-object.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "fsck.h" #include "config.h" diff --git a/builtin/mktree.c b/builtin/mktree.c index 3c16faa40e..7ffe6eefd8 100644 --- a/builtin/mktree.c +++ b/builtin/mktree.c @@ -11,7 +11,8 @@ #include "strbuf.h" #include "tree.h" #include "parse-options.h" -#include "object-store-ll.h" +#include "object-file.h" +#include "object-store.h" static struct treeent { unsigned mode; diff --git a/builtin/multi-pack-index.c b/builtin/multi-pack-index.c index 2a938466f5..d98410ca6c 100644 --- a/builtin/multi-pack-index.c +++ b/builtin/multi-pack-index.c @@ -7,7 +7,7 @@ #include "midx.h" #include "strbuf.h" #include "trace2.h" -#include "object-store-ll.h" +#include "object-store.h" #include "replace-object.h" #include "repository.h" diff --git a/builtin/mv.c b/builtin/mv.c index d673a6c83e..54b323fff7 100644 --- a/builtin/mv.c +++ b/builtin/mv.c @@ -15,6 +15,7 @@ #include "gettext.h" #include "name-hash.h" #include "object-file.h" +#include "path.h" #include "pathspec.h" #include "lockfile.h" #include "dir.h" @@ -556,7 +557,7 @@ remove_entry: */ char *dst_dup = xstrdup(dst); string_list_append(&dirty_paths, dst); - safe_create_leading_directories(dst_dup); + safe_create_leading_directories(the_repository, dst_dup); FREE_AND_NULL(dst_dup); rename(src, dst); } diff --git a/builtin/notes.c b/builtin/notes.c index ff61ec5f2d..a3f433ca4c 100644 --- a/builtin/notes.c +++ b/builtin/notes.c @@ -14,8 +14,9 @@ #include "gettext.h" #include "hex.h" #include "notes.h" +#include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "path.h" #include "pretty.h" diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 3973267e9e..8174c60c70 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -32,7 +32,7 @@ #include "list.h" #include "packfile.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "replace-object.h" #include "dir.h" #include "midx.h" diff --git a/builtin/pack-redundant.c b/builtin/pack-redundant.c index 3febe732f8..5d1fc78176 100644 --- a/builtin/pack-redundant.c +++ b/builtin/pack-redundant.c @@ -13,7 +13,7 @@ #include "hex.h" #include "packfile.h" -#include "object-store-ll.h" +#include "object-store.h" #include "strbuf.h" #define BLKSIZE 512 diff --git a/builtin/prune.c b/builtin/prune.c index 8f52da8bd6..e930caa0c0 100644 --- a/builtin/prune.c +++ b/builtin/prune.c @@ -17,7 +17,7 @@ #include "replace-object.h" #include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "shallow.h" static const char * const prune_usage[] = { diff --git a/builtin/rebase.c b/builtin/rebase.c index 965bd048a8..36e336009c 100644 --- a/builtin/rebase.c +++ b/builtin/rebase.c @@ -267,7 +267,8 @@ static int init_basic_state(struct replay_opts *opts, const char *head_name, { FILE *interactive; - if (!is_directory(merge_dir()) && mkdir_in_gitdir(merge_dir())) + if (!is_directory(merge_dir()) && + safe_create_dir_in_gitdir(the_repository, merge_dir())) return error_errno(_("could not create temporary %s"), merge_dir()); refs_delete_reflog(get_main_ref_store(the_repository), "REBASE_HEAD"); diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c index b3e2a9d0c6..be314879e8 100644 --- a/builtin/receive-pack.c +++ b/builtin/receive-pack.c @@ -31,8 +31,9 @@ #include "tmp-objdir.h" #include "oidset.h" #include "packfile.h" +#include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "path.h" #include "protocol.h" #include "commit-reach.h" diff --git a/builtin/remote.c b/builtin/remote.c index d2aeb5ba1f..b4baa34e66 100644 --- a/builtin/remote.c +++ b/builtin/remote.c @@ -14,7 +14,7 @@ #include "rebase.h" #include "refs.h" #include "refspec.h" -#include "object-store-ll.h" +#include "object-store.h" #include "strvec.h" #include "commit-reach.h" #include "progress.h" diff --git a/builtin/repack.c b/builtin/repack.c index f3330ade7b..1fd2874324 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -17,7 +17,7 @@ #include "midx.h" #include "packfile.h" #include "prune-packed.h" -#include "object-store-ll.h" +#include "object-store.h" #include "promisor-remote.h" #include "shallow.h" #include "pack.h" diff --git a/builtin/replace.c b/builtin/replace.c index 15ec0922ce..48c7c6a2d5 100644 --- a/builtin/replace.c +++ b/builtin/replace.c @@ -19,7 +19,7 @@ #include "run-command.h" #include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "replace-object.h" #include "tag.h" #include "wildmatch.h" @@ -305,7 +305,7 @@ static int import_object(struct object_id *oid, enum object_type type, strbuf_release(&result); } else { struct stat st; - int flags = HASH_FORMAT_CHECK | HASH_WRITE_OBJECT; + int flags = INDEX_FORMAT_CHECK | INDEX_WRITE_OBJECT; if (fstat(fd, &st) < 0) { error_errno(_("unable to fstat %s"), filename); diff --git a/builtin/rev-list.c b/builtin/rev-list.c index 4a84f18f9e..c4cd4ed5c8 100644 --- a/builtin/rev-list.c +++ b/builtin/rev-list.c @@ -14,7 +14,7 @@ #include "object.h" #include "object-name.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "pack-bitmap.h" #include "parse-options.h" #include "log-tree.h" diff --git a/builtin/show-ref.c b/builtin/show-ref.c index 285cd3e433..f81209f23c 100644 --- a/builtin/show-ref.c +++ b/builtin/show-ref.c @@ -5,7 +5,7 @@ #include "hex.h" #include "refs/refs-internal.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "object.h" #include "string-list.h" #include "parse-options.h" diff --git a/builtin/sparse-checkout.c b/builtin/sparse-checkout.c index 14dcace5f8..1bf01591b2 100644 --- a/builtin/sparse-checkout.c +++ b/builtin/sparse-checkout.c @@ -9,6 +9,7 @@ #include "object-file.h" #include "object-name.h" #include "parse-options.h" +#include "path.h" #include "pathspec.h" #include "strbuf.h" #include "string-list.h" @@ -335,7 +336,7 @@ static int write_patterns_and_update(struct pattern_list *pl) sparse_filename = get_sparse_checkout_filename(); - if (safe_create_leading_directories(sparse_filename)) + if (safe_create_leading_directories(the_repository, sparse_filename)) die(_("failed to create directory for sparse-checkout file")); hold_lock_file_for_update(&lk, sparse_filename, LOCK_DIE_ON_ERROR); @@ -491,7 +492,7 @@ static int sparse_checkout_init(int argc, const char **argv, const char *prefix, FILE *fp; /* assume we are in a fresh repo, but update the sparse-checkout file */ - if (safe_create_leading_directories(sparse_filename)) + if (safe_create_leading_directories(the_repository, sparse_filename)) die(_("unable to create leading directories of %s"), sparse_filename); fp = xfopen(sparse_filename, "w"); diff --git a/builtin/submodule--helper.c b/builtin/submodule--helper.c index 570226ea16..53da2116dd 100644 --- a/builtin/submodule--helper.c +++ b/builtin/submodule--helper.c @@ -28,7 +28,7 @@ #include "diff.h" #include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "advice.h" #include "branch.h" #include "list-objects-filter-options.h" @@ -1739,7 +1739,7 @@ static int clone_submodule(const struct module_clone_data *clone_data, !is_empty_dir(clone_data_path)) die(_("directory not empty: '%s'"), clone_data_path); - if (safe_create_leading_directories_const(sm_gitdir) < 0) + if (safe_create_leading_directories_const(the_repository, sm_gitdir) < 0) die(_("could not create directory '%s'"), sm_gitdir); prepare_possible_alternates(clone_data->name, reference); @@ -1800,7 +1800,7 @@ static int clone_submodule(const struct module_clone_data *clone_data, if (clone_data->require_init && !stat(clone_data_path, &st) && !is_empty_dir(clone_data_path)) die(_("directory not empty: '%s'"), clone_data_path); - if (safe_create_leading_directories_const(clone_data_path) < 0) + if (safe_create_leading_directories_const(the_repository, clone_data_path) < 0) die(_("could not create directory '%s'"), clone_data_path); path = xstrfmt("%s/index", sm_gitdir); unlink_or_warn(path); diff --git a/builtin/tag.c b/builtin/tag.c index 7c173535cb..e6b372cebf 100644 --- a/builtin/tag.c +++ b/builtin/tag.c @@ -17,8 +17,9 @@ #include "gettext.h" #include "hex.h" #include "refs.h" +#include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "path.h" #include "tag.h" #include "parse-options.h" diff --git a/builtin/unpack-file.c b/builtin/unpack-file.c index fb5fcbc40a..e33acfc4ee 100644 --- a/builtin/unpack-file.c +++ b/builtin/unpack-file.c @@ -2,8 +2,9 @@ #include "builtin.h" #include "config.h" #include "hex.h" +#include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" static char *create_temp_file(struct object_id *oid) { diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c index 3bbcaf2de9..661be789f1 100644 --- a/builtin/unpack-objects.c +++ b/builtin/unpack-objects.c @@ -8,7 +8,8 @@ #include "gettext.h" #include "git-zlib.h" #include "hex.h" -#include "object-store-ll.h" +#include "object-file.h" +#include "object-store.h" #include "object.h" #include "delta.h" #include "pack.h" diff --git a/builtin/update-index.c b/builtin/update-index.c index b2f6b1a3fb..f0cf964294 100644 --- a/builtin/update-index.c +++ b/builtin/update-index.c @@ -304,7 +304,7 @@ static int add_one_path(const struct cache_entry *old, const char *path, int len ce->ce_mode = ce_mode_from_stat(old, st->st_mode); if (index_path(the_repository->index, &ce->oid, path, st, - info_only ? 0 : HASH_WRITE_OBJECT)) { + info_only ? 0 : INDEX_WRITE_OBJECT)) { discard_cache_entry(ce); return -1; } diff --git a/builtin/worktree.c b/builtin/worktree.c index 87ccd47794..88a36ea9f8 100644 --- a/builtin/worktree.c +++ b/builtin/worktree.c @@ -348,7 +348,7 @@ static void copy_sparse_checkout(const char *worktree_git_dir) char *to_file = xstrfmt("%s/info/sparse-checkout", worktree_git_dir); if (file_exists(from_file)) { - if (safe_create_leading_directories(to_file) || + if (safe_create_leading_directories(the_repository, to_file) || copy_file(to_file, from_file, 0666)) error(_("failed to copy '%s' to '%s'; sparse-checkout may not work correctly"), from_file, to_file); @@ -367,7 +367,7 @@ static void copy_filtered_worktree_config(const char *worktree_git_dir) struct config_set cs = { { 0 } }; int bare; - if (safe_create_leading_directories(to_file) || + if (safe_create_leading_directories(the_repository, to_file) || copy_file(to_file, from_file, 0666)) { error(_("failed to copy worktree config from '%s' to '%s'"), from_file, to_file); @@ -466,7 +466,7 @@ static int add_worktree(const char *path, const char *refname, name = sb_name.buf; repo_git_path_replace(the_repository, &sb_repo, "worktrees/%s", name); len = sb_repo.len; - if (safe_create_leading_directories_const(sb_repo.buf)) + if (safe_create_leading_directories_const(the_repository, sb_repo.buf)) die_errno(_("could not create leading directories of '%s'"), sb_repo.buf); @@ -498,7 +498,7 @@ static int add_worktree(const char *path, const char *refname, write_file(sb.buf, _("initializing")); strbuf_addf(&sb_git, "%s/.git", path); - if (safe_create_leading_directories_const(sb_git.buf)) + if (safe_create_leading_directories_const(the_repository, sb_git.buf)) die_errno(_("could not create leading directories of '%s'"), sb_git.buf); junk_work_tree = xstrdup(path); diff --git a/bulk-checkin.c b/bulk-checkin.c index 79696e80f2..c31c31b18d 100644 --- a/bulk-checkin.c +++ b/bulk-checkin.c @@ -17,7 +17,7 @@ #include "tmp-objdir.h" #include "packfile.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" static int odb_transaction_nesting; @@ -167,7 +167,7 @@ static int stream_blob_to_pack(struct bulk_checkin_packfile *state, unsigned char obuf[16384]; unsigned hdrlen; int status = Z_OK; - int write_object = (flags & HASH_WRITE_OBJECT); + int write_object = (flags & INDEX_WRITE_OBJECT); off_t offset = 0; git_deflate_init(&s, pack_compression_level); @@ -237,7 +237,7 @@ static int stream_blob_to_pack(struct bulk_checkin_packfile *state, static void prepare_to_stream(struct bulk_checkin_packfile *state, unsigned flags) { - if (!(flags & HASH_WRITE_OBJECT) || state->f) + if (!(flags & INDEX_WRITE_OBJECT) || state->f) return; state->f = create_tmp_packfile(the_repository, &state->pack_tmp_name); @@ -271,7 +271,7 @@ static int deflate_blob_to_pack(struct bulk_checkin_packfile *state, git_hash_update(&ctx, obuf, header_len); /* Note: idx is non-NULL when we are writing */ - if ((flags & HASH_WRITE_OBJECT) != 0) { + if ((flags & INDEX_WRITE_OBJECT) != 0) { CALLOC_ARRAY(idx, 1); prepare_to_stream(state, flags); diff --git a/bulk-checkin.h b/bulk-checkin.h index aa7286a7b3..7246ea58dc 100644 --- a/bulk-checkin.h +++ b/bulk-checkin.h @@ -9,6 +9,21 @@ void prepare_loose_object_bulk_checkin(void); void fsync_loose_object_bulk_checkin(int fd, const char *filename); +/* + * 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. + */ int index_blob_bulk_checkin(struct object_id *oid, int fd, size_t size, const char *path, unsigned flags); diff --git a/bundle-uri.c b/bundle-uri.c index 744257c49c..96d2ba726d 100644 --- a/bundle-uri.c +++ b/bundle-uri.c @@ -14,7 +14,7 @@ #include "fetch-pack.h" #include "remote.h" #include "trace2.h" -#include "object-store-ll.h" +#include "object-store.h" static struct { enum bundle_list_heuristic heuristic; diff --git a/bundle.c b/bundle.c index 0614426e20..b0a3fee2ef 100644 --- a/bundle.c +++ b/bundle.c @@ -7,7 +7,7 @@ #include "environment.h" #include "gettext.h" #include "hex.h" -#include "object-store-ll.h" +#include "object-store.h" #include "repository.h" #include "object.h" #include "commit.h" diff --git a/cache-tree.c b/cache-tree.c index bcbcad3d61..c0e1e9ee1d 100644 --- a/cache-tree.c +++ b/cache-tree.c @@ -10,7 +10,7 @@ #include "cache-tree.h" #include "bulk-checkin.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "read-cache-ll.h" #include "replace-object.h" #include "repository.h" @@ -452,7 +452,7 @@ static int update_one(struct cache_tree *it, OBJ_TREE, &it->oid); } else if (write_object_file_flags(buffer.buf, buffer.len, OBJ_TREE, &it->oid, NULL, flags & WRITE_TREE_SILENT - ? HASH_SILENT : 0)) { + ? WRITE_OBJECT_FILE_SILENT : 0)) { strbuf_release(&buffer); return -1; } diff --git a/combine-diff.c b/combine-diff.c index 553bf59fed..dfae9f7995 100644 --- a/combine-diff.c +++ b/combine-diff.c @@ -2,7 +2,7 @@ #define DISABLE_SIGN_COMPARE_WARNINGS #include "git-compat-util.h" -#include "object-store-ll.h" +#include "object-store.h" #include "commit.h" #include "convert.h" #include "diff.h" diff --git a/commit-graph.c b/commit-graph.c index 8286d5dda2..6394752b0b 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -13,8 +13,7 @@ #include "refs.h" #include "hash-lookup.h" #include "commit-graph.h" -#include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "oid-array.h" #include "path.h" #include "alloc.h" @@ -2065,7 +2064,7 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx) ctx->graph_name = get_commit_graph_filename(ctx->odb); } - if (safe_create_leading_directories(ctx->graph_name)) { + if (safe_create_leading_directories(the_repository, ctx->graph_name)) { error(_("unable to create leading directories of %s"), ctx->graph_name); return -1; diff --git a/commit-graph.h b/commit-graph.h index 6781940195..13f662827d 100644 --- a/commit-graph.h +++ b/commit-graph.h @@ -1,7 +1,7 @@ #ifndef COMMIT_GRAPH_H #define COMMIT_GRAPH_H -#include "object-store-ll.h" +#include "object-store.h" #include "oidset.h" #define GIT_TEST_COMMIT_GRAPH "GIT_TEST_COMMIT_GRAPH" diff --git a/commit.c b/commit.c index 1f64daa9f4..e915b2b9a1 100644 --- a/commit.c +++ b/commit.c @@ -9,7 +9,7 @@ #include "hex.h" #include "repository.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "utf8.h" #include "diff.h" #include "revision.h" @@ -29,6 +29,7 @@ #include "tree.h" #include "hook.h" #include "parse.h" +#include "object-file.h" #include "object-file-convert.h" static struct commit_extra_header *read_commit_extra_header_lines(const char *buf, size_t len, const char **); diff --git a/compat/open.c b/compat/open.c index eb3754a23b..37ae2b1aeb 100644 --- a/compat/open.c +++ b/compat/open.c @@ -1,5 +1,6 @@ #include "git-compat-util.h" +#ifdef OPEN_RETURNS_EINTR #undef open int git_open_with_retry(const char *path, int flags, ...) { @@ -23,3 +24,31 @@ int git_open_with_retry(const char *path, int flags, ...) return ret; } +#endif + +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; +} diff --git a/config.c b/config.c index accb47e2d1..b18b5617fc 100644 --- a/config.c +++ b/config.c @@ -31,7 +31,7 @@ #include "hashmap.h" #include "string-list.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "pager.h" #include "path.h" #include "utf8.h" diff --git a/connected.c b/connected.c index 3099da84f3..4415388beb 100644 --- a/connected.c +++ b/connected.c @@ -3,7 +3,7 @@ #include "git-compat-util.h" #include "gettext.h" #include "hex.h" -#include "object-store-ll.h" +#include "object-store.h" #include "run-command.h" #include "sigchain.h" #include "connected.h" diff --git a/convert.c b/convert.c index 9cc0ca20ca..8783e17941 100644 --- a/convert.c +++ b/convert.c @@ -8,7 +8,7 @@ #include "copy.h" #include "gettext.h" #include "hex.h" -#include "object-store-ll.h" +#include "object-store.h" #include "attr.h" #include "run-command.h" #include "quote.h" diff --git a/diagnose.c b/diagnose.c index bd485effea..b1be74be98 100644 --- a/diagnose.c +++ b/diagnose.c @@ -7,7 +7,7 @@ #include "gettext.h" #include "hex.h" #include "strvec.h" -#include "object-store-ll.h" +#include "object-store.h" #include "packfile.h" #include "parse-options.h" #include "repository.h" diff --git a/diff.c b/diff.c index 3bcf502883..91d5b962b5 100644 --- a/diff.c +++ b/diff.c @@ -23,7 +23,7 @@ #include "color.h" #include "run-command.h" #include "utf8.h" -#include "object-store-ll.h" +#include "object-store.h" #include "userdiff.h" #include "submodule.h" #include "hashmap.h" diff --git a/diffcore-rename.c b/diffcore-rename.c index 8077283fc7..179731462b 100644 --- a/diffcore-rename.c +++ b/diffcore-rename.c @@ -8,7 +8,7 @@ #include "git-compat-util.h" #include "diff.h" #include "diffcore.h" -#include "object-store-ll.h" +#include "object-store.h" #include "hashmap.h" #include "mem-pool.h" #include "oid-array.h" diff --git a/dir.c b/dir.c index 28b0e03feb..5c4675b4ac 100644 --- a/dir.c +++ b/dir.c @@ -17,8 +17,7 @@ #include "environment.h" #include "gettext.h" #include "name-hash.h" -#include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "path.h" #include "refs.h" #include "repository.h" @@ -4063,12 +4062,12 @@ void connect_work_tree_and_git_dir(const char *work_tree_, /* Prepare .git file */ strbuf_addf(&gitfile_sb, "%s/.git", work_tree_); - if (safe_create_leading_directories_const(gitfile_sb.buf)) + if (safe_create_leading_directories_const(the_repository, gitfile_sb.buf)) die(_("could not create directories for %s"), gitfile_sb.buf); /* Prepare config file */ strbuf_addf(&cfg_sb, "%s/config", git_dir_); - if (safe_create_leading_directories_const(cfg_sb.buf)) + if (safe_create_leading_directories_const(the_repository, cfg_sb.buf)) die(_("could not create directories for %s"), cfg_sb.buf); git_dir = real_pathdup(git_dir_, 1); diff --git a/entry.c b/entry.c index 81b321e53d..f36ec5ad24 100644 --- a/entry.c +++ b/entry.c @@ -1,7 +1,7 @@ #define USE_THE_REPOSITORY_VARIABLE #include "git-compat-util.h" -#include "object-store-ll.h" +#include "object-store.h" #include "dir.h" #include "environment.h" #include "gettext.h" diff --git a/fetch-pack.c b/fetch-pack.c index 1ed5e11dd5..210dc30d50 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -24,7 +24,7 @@ #include "oid-array.h" #include "oidset.h" #include "packfile.h" -#include "object-store-ll.h" +#include "object-store.h" #include "path.h" #include "connected.h" #include "fetch-negotiator.h" diff --git a/fmt-merge-msg.c b/fmt-merge-msg.c index 5b63c3b088..501b5acdd4 100644 --- a/fmt-merge-msg.c +++ b/fmt-merge-msg.c @@ -6,7 +6,7 @@ #include "environment.h" #include "refs.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "diff.h" #include "diff-merges.h" #include "hex.h" diff --git a/fsck.c b/fsck.c index 9fc4c25ffd..8dc8472ceb 100644 --- a/fsck.c +++ b/fsck.c @@ -4,7 +4,7 @@ #include "date.h" #include "dir.h" #include "hex.h" -#include "object-store-ll.h" +#include "object-store.h" #include "path.h" #include "repository.h" #include "object.h" diff --git a/git-compat-util.h b/git-compat-util.h index afa040086f..591bb78ad9 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -598,6 +598,9 @@ static inline bool strip_suffix(const char *str, const char *suffix, #define DEFAULT_PACKED_GIT_LIMIT \ ((1024L * 1024L) * (size_t)(sizeof(void*) >= 8 ? (32 * 1024L * 1024L) : 256)) +int git_open_cloexec(const char *name, int flags); +#define git_open(name) git_open_cloexec(name, O_RDONLY) + static inline size_t st_add(size_t a, size_t b) { if (unsigned_add_overflows(a, b)) diff --git a/grep.c b/grep.c index 9284b5741f..f8d535182c 100644 --- a/grep.c +++ b/grep.c @@ -5,7 +5,7 @@ #include "gettext.h" #include "grep.h" #include "hex.h" -#include "object-store-ll.h" +#include "object-store.h" #include "pretty.h" #include "userdiff.h" #include "xdiff-interface.h" diff --git a/http-backend.c b/http-backend.c index 50b2858fad..0c575aa88a 100644 --- a/http-backend.c +++ b/http-backend.c @@ -18,7 +18,7 @@ #include "url.h" #include "strvec.h" #include "packfile.h" -#include "object-store-ll.h" +#include "object-store.h" #include "protocol.h" #include "date.h" #include "write-or-die.h" diff --git a/http-push.c b/http-push.c index 1b030d96f4..32e37565f4 100644 --- a/http-push.c +++ b/http-push.c @@ -19,7 +19,8 @@ #include "tree-walk.h" #include "url.h" #include "packfile.h" -#include "object-store-ll.h" +#include "object-file.h" +#include "object-store.h" #include "commit-reach.h" #ifdef EXPAT_NEEDS_XMLPARSE_H diff --git a/http-walker.c b/http-walker.c index 7918ddc096..882cae19c2 100644 --- a/http-walker.c +++ b/http-walker.c @@ -9,7 +9,7 @@ #include "list.h" #include "transport.h" #include "packfile.h" -#include "object-store-ll.h" +#include "object-store.h" struct alt_base { char *base; diff --git a/http.c b/http.c index d21e3a3bad..0c41138042 100644 --- a/http.c +++ b/http.c @@ -19,7 +19,7 @@ #include "packfile.h" #include "string-list.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "tempfile.h" static struct trace_key trace_curl = TRACE_KEY_INIT(CURL); diff --git a/list-objects-filter.c b/list-objects-filter.c index dc598a081b..7765761b3c 100644 --- a/list-objects-filter.c +++ b/list-objects-filter.c @@ -12,7 +12,7 @@ #include "oidmap.h" #include "oidset.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" /* Remember to update object flag allocation in object.h */ /* diff --git a/list-objects.c b/list-objects.c index 943e62e868..1e5512e131 100644 --- a/list-objects.c +++ b/list-objects.c @@ -14,7 +14,7 @@ #include "list-objects-filter.h" #include "list-objects-filter-options.h" #include "packfile.h" -#include "object-store-ll.h" +#include "object-store.h" #include "trace.h" #include "environment.h" diff --git a/log-tree.c b/log-tree.c index 5dd1b63076..a4d4ab59ca 100644 --- a/log-tree.c +++ b/log-tree.c @@ -9,7 +9,7 @@ #include "environment.h" #include "hex.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "repository.h" #include "tmp-objdir.h" #include "commit.h" diff --git a/mailmap.c b/mailmap.c index f35d20ed7f..9e2642a043 100644 --- a/mailmap.c +++ b/mailmap.c @@ -6,7 +6,7 @@ #include "string-list.h" #include "mailmap.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "setup.h" char *git_mailmap_file; diff --git a/match-trees.c b/match-trees.c index ef14ceb594..72922d5d64 100644 --- a/match-trees.c +++ b/match-trees.c @@ -6,7 +6,8 @@ #include "strbuf.h" #include "tree.h" #include "tree-walk.h" -#include "object-store-ll.h" +#include "object-file.h" +#include "object-store.h" #include "repository.h" static int score_missing(unsigned mode) diff --git a/merge-blobs.c b/merge-blobs.c index 0ad0390fea..53f36dbc17 100644 --- a/merge-blobs.c +++ b/merge-blobs.c @@ -4,7 +4,7 @@ #include "merge-ll.h" #include "blob.h" #include "merge-blobs.h" -#include "object-store-ll.h" +#include "object-store.h" static int fill_mmfile_blob(mmfile_t *f, struct blob *obj) { diff --git a/merge-ort.c b/merge-ort.c index 6dbb680ede..77310a4a52 100644 --- a/merge-ort.c +++ b/merge-ort.c @@ -37,8 +37,9 @@ #include "merge-ll.h" #include "match-trees.h" #include "mem-pool.h" +#include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "oid-array.h" #include "path.h" #include "promisor-remote.h" diff --git a/meson.build b/meson.build index c47cb79af0..b906e78d89 100644 --- a/meson.build +++ b/meson.build @@ -296,6 +296,7 @@ libgit_sources = [ 'common-init.c', 'compat/nonblock.c', 'compat/obstack.c', + 'compat/open.c', 'compat/terminal.c', 'compiler-tricks/not-constant.c', 'config.c', @@ -386,6 +387,7 @@ libgit_sources = [ 'object-file-convert.c', 'object-file.c', 'object-name.c', + 'object-store.c', 'object.c', 'oid-array.c', 'oidmap.c', diff --git a/midx-write.c b/midx-write.c index 48a4dc5e94..dd3b3070e5 100644 --- a/midx-write.c +++ b/midx-write.c @@ -1098,7 +1098,7 @@ static int write_midx_internal(struct repository *r, const char *object_dir, object_dir); else get_midx_filename(r->hash_algo, &midx_name, object_dir); - if (safe_create_leading_directories(midx_name.buf)) + if (safe_create_leading_directories(r, midx_name.buf)) die_errno(_("unable to create leading directories of %s"), midx_name.buf); diff --git a/midx.c b/midx.c index 807fdf72f7..3d0015f782 100644 --- a/midx.c +++ b/midx.c @@ -5,7 +5,6 @@ #include "dir.h" #include "hex.h" #include "packfile.h" -#include "object-file.h" #include "hash-lookup.h" #include "midx.h" #include "progress.h" diff --git a/notes-cache.c b/notes-cache.c index ecfdf6e43b..150241b15e 100644 --- a/notes-cache.c +++ b/notes-cache.c @@ -2,7 +2,8 @@ #include "git-compat-util.h" #include "notes-cache.h" -#include "object-store-ll.h" +#include "object-file.h" +#include "object-store.h" #include "pretty.h" #include "repository.h" #include "commit.h" diff --git a/notes-merge.c b/notes-merge.c index 5008faef45..dae8e6a281 100644 --- a/notes-merge.c +++ b/notes-merge.c @@ -8,7 +8,7 @@ #include "refs.h" #include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "path.h" #include "repository.h" #include "diff.h" @@ -296,7 +296,7 @@ static void check_notes_merge_worktree(struct notes_merge_options *o) "(%s exists)."), repo_git_path_replace(the_repository, &buf, "NOTES_MERGE_*")); } - if (safe_create_leading_directories_const(repo_git_path_replace(the_repository, &buf, + if (safe_create_leading_directories_const(the_repository, repo_git_path_replace(the_repository, &buf, NOTES_MERGE_WORKTREE "/.test"))) die_errno("unable to create directory %s", repo_git_path_replace(the_repository, &buf, NOTES_MERGE_WORKTREE)); @@ -314,7 +314,7 @@ static void write_buf_to_worktree(const struct object_id *obj, { int fd; char *path = repo_git_path(the_repository, NOTES_MERGE_WORKTREE "/%s", oid_to_hex(obj)); - if (safe_create_leading_directories_const(path)) + if (safe_create_leading_directories_const(the_repository, path)) die_errno("unable to create directory for '%s'", path); fd = xopen(path, O_WRONLY | O_EXCL | O_CREAT, 0666); @@ -729,7 +729,7 @@ int notes_merge_commit(struct notes_merge_options *o, /* write file as blob, and add to partial_tree */ if (stat(path.buf, &st)) die_errno("Failed to stat '%s'", path.buf); - if (index_path(o->repo->index, &blob_oid, path.buf, &st, HASH_WRITE_OBJECT)) + if (index_path(o->repo->index, &blob_oid, path.buf, &st, INDEX_WRITE_OBJECT)) die("Failed to write blob object from '%s'", path.buf); if (add_note(partial_tree, &obj_oid, &blob_oid, NULL)) die("Failed to add resolved note '%s' to notes tree", diff --git a/notes.c b/notes.c index ce5a1006a8..d9645c4b5d 100644 --- a/notes.c +++ b/notes.c @@ -6,8 +6,9 @@ #include "environment.h" #include "hex.h" #include "notes.h" +#include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "utf8.h" #include "strbuf.h" #include "tree-walk.h" diff --git a/object-file.c b/object-file.c index f3810871f0..9cc3a24a40 100644 --- a/object-file.c +++ b/object-file.c @@ -11,225 +11,37 @@ #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 "oidtree.h" +#include "pack.h" +#include "packfile.h" #include "path.h" -#include "promisor-remote.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 -/* - * 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(the_repository, 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(the_repository, 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; - repo_git_path_replace(the_repository, 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 */ - repo_git_path_replace(the_repository, 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) { int i; @@ -243,9 +55,9 @@ 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 object_directory *odb, + struct strbuf *buf, + const struct object_id *oid) { strbuf_reset(buf); strbuf_addstr(buf, odb->path); @@ -254,513 +66,6 @@ static const char *odb_loose_path(struct object_directory *odb, 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 = repo_git_path(the_repository, "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) { @@ -825,54 +130,6 @@ 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) { @@ -940,33 +197,6 @@ int stream_object_signature(struct repository *r, const struct object_id *oid) 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. @@ -1235,9 +465,9 @@ 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; @@ -1335,345 +565,6 @@ cleanup: 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(the_repository, &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, struct git_hash_ctx *c, const void *buf, unsigned long len, struct object_id *oid, @@ -1945,7 +836,7 @@ static int start_loose_object_common(struct strbuf *tmp_file, fd = create_tmpfile(tmp_file, filename); if (fd < 0) { - if (flags & HASH_SILENT) + if (flags & WRITE_OBJECT_FILE_SILENT) return -1; else if (errno == EACCES) return error(_("insufficient permission for adding " @@ -2077,7 +968,7 @@ static int write_loose_object(const struct object_id *oid, char *hdr, utb.actime = mtime; utb.modtime = mtime; if (utime(tmp_file.buf, &utb) < 0 && - !(flags & HASH_SILENT)) + !(flags & WRITE_OBJECT_FILE_SILENT)) warning_errno(_("failed utime() on %s"), tmp_file.buf); } @@ -2196,7 +1087,8 @@ 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(the_repository, dir.buf) && + errno != EEXIST) { err = error_errno(_("unable to create directory %s"), dir.buf); strbuf_release(&dir); goto cleanup; @@ -2288,7 +1180,7 @@ int write_object_file_literally(const void *buf, unsigned long len, write_object_file_prepare_literally(the_hash_algo, buf, len, type, oid, header, &hdrlen); - if (!(flags & HASH_WRITE_OBJECT)) + if (!(flags & WRITE_OBJECT_FILE_PERSIST)) goto cleanup; if (freshen_packed_object(oid) || freshen_loose_object(oid)) goto cleanup; @@ -2335,32 +1227,6 @@ int force_object_loose(const struct object_id *oid, time_t mtime) 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, @@ -2385,7 +1251,7 @@ 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; @@ -2400,7 +1266,7 @@ 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; @@ -2426,7 +1292,7 @@ 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); @@ -2491,28 +1357,6 @@ 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) @@ -2533,8 +1377,8 @@ int index_fd(struct index_state *istate, struct object_id *oid, 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; } @@ -2558,7 +1402,7 @@ 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)) + if (!(flags & INDEX_WRITE_OBJECT)) hash_object_file(the_hash_algo, sb.buf, sb.len, OBJ_BLOB, oid); else if (write_object_file(sb.buf, sb.len, OBJ_BLOB, oid)) @@ -2588,16 +1432,6 @@ 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, diff --git a/object-file.h b/object-file.h index 81b30d269c..c002fbe234 100644 --- a/object-file.h +++ b/object-file.h @@ -14,50 +14,37 @@ struct index_state; */ extern int fetch_if_missing; -#define HASH_WRITE_OBJECT 1 -#define HASH_FORMAT_CHECK 2 -#define HASH_RENORMALIZE 4 -#define HASH_SILENT 8 +enum { + INDEX_WRITE_OBJECT = (1 << 0), + INDEX_FORMAT_CHECK = (1 << 1), + INDEX_RENORMALIZE = (1 << 2), +}; + 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); int index_path(struct index_state *istate, struct object_id *oid, const char *path, struct stat *st, unsigned flags); +struct object_directory; + +const char *odb_loose_path(struct object_directory *odb, + struct strbuf *buf, + const struct object_id *oid); + /* - * Create the directory containing the named path, using care to be - * somewhat safe against races. Return one of the scld_error values to - * indicate success/failure. On error, set errno to describe the - * problem. - * - * SCLD_VANISHED indicates that one of the ancestor directories of the - * path existed at one point during the function call and then - * suddenly vanished, probably because another process pruned the - * directory while we were working. To be robust against this kind of - * race, callers might want to try invoking the function again when it - * returns SCLD_VANISHED. - * - * safe_create_leading_directories() temporarily changes path while it - * is working but restores it before returning. - * safe_create_leading_directories_const() doesn't modify path, even - * temporarily. Both these variants adjust the permissions of the - * created directories to honor core.sharedRepository, so they are best - * suited for files inside the git dir. For working tree files, use - * safe_create_leading_directories_no_share() instead, as it ignores - * the core.sharedRepository setting. + * Return true iff an alternate object database has a loose object + * with the specified name. This function does not respect replace + * references. */ -enum scld_error { - SCLD_OK = 0, - SCLD_FAILED = -1, - SCLD_PERMS = -2, - SCLD_EXISTS = -3, - SCLD_VANISHED = -4 -}; -enum scld_error safe_create_leading_directories(char *path); -enum scld_error safe_create_leading_directories_const(const char *path); -enum scld_error safe_create_leading_directories_no_share(char *path); +int has_loose_object_nonlocal(const struct object_id *); -int mkdir_in_gitdir(const char *path); +int has_loose_object(const struct object_id *); -int git_open_cloexec(const char *name, int flags); -#define git_open(name) git_open_cloexec(name, O_RDONLY) +/** + * format_object_header() is a thin wrapper around s xsnprintf() that + * writes the initial " " part of the loose object + * header. It returns the size that snprintf() returns + 1. + */ +int format_object_header(char *str, size_t size, enum object_type type, + size_t objsize); /** * unpack_loose_header() initializes the data stream needed to unpack @@ -99,6 +86,44 @@ enum unpack_loose_header_result unpack_loose_header(git_zstream *stream, struct object_info; int parse_loose_header(const char *hdr, struct object_info *oi); +enum { + /* + * By default, `write_object_file_literally()` does not actually write + * anything into the object store, but only computes the object ID. + * This flag changes that so that the object will be written as a loose + * object and persisted. + */ + WRITE_OBJECT_FILE_PERSIST = (1 << 0), + + /* + * Do not print an error in case something gose wrong. + */ + WRITE_OBJECT_FILE_SILENT = (1 << 1), +}; + +int write_object_file_flags(const void *buf, unsigned long len, + enum object_type type, struct object_id *oid, + struct object_id *comapt_oid_in, unsigned flags); +static inline int write_object_file(const void *buf, unsigned long len, + enum object_type type, struct object_id *oid) +{ + return write_object_file_flags(buf, len, type, oid, NULL, 0); +} + +struct input_stream { + const void *(*read)(struct input_stream *, unsigned long *len); + void *data; + int is_finished; +}; + +int write_object_file_literally(const void *buf, unsigned long len, + const char *type, struct object_id *oid, + unsigned flags); +int stream_loose_object(struct input_stream *in_stream, size_t len, + struct object_id *oid); + +int force_object_loose(const struct object_id *oid, time_t mtime); + /** * With in-core object data in "buf", rehash it to make sure the * object name actually matches "oid" to detect object corruption. @@ -117,6 +142,10 @@ int check_object_signature(struct repository *r, const struct object_id *oid, */ int stream_object_signature(struct repository *r, const struct object_id *oid); +int loose_object_info(struct repository *r, + const struct object_id *oid, + struct object_info *oi, int flags); + enum finalize_object_file_flags { FOF_SKIP_COLLISION_CHECK = 1, }; @@ -128,10 +157,18 @@ int finalize_object_file_flags(const char *tmpfile, const char *filename, /* Helper to check and "touch" a file */ int check_and_freshen_file(const char *fn, int freshen); -void *read_object_with_reference(struct repository *r, - const struct object_id *oid, - enum object_type required_type, - unsigned long *size, - struct object_id *oid_ret); +/* + * Open the loose object at path, check its hash, and return the contents, + * use the "oi" argument to assert things about the object, or e.g. populate its + * type, and size. If the object is a blob, then "contents" may return NULL, + * to allow streaming of large blobs. + * + * Returns 0 on success, negative on error (details may be written to stderr). + */ +int read_loose_object(const char *path, + const struct object_id *expected_oid, + struct object_id *real_oid, + void **contents, + struct object_info *oi); #endif /* OBJECT_FILE_H */ diff --git a/object-name.c b/object-name.c index 91f731373a..2c751a5352 100644 --- a/object-name.c +++ b/object-name.c @@ -19,7 +19,7 @@ #include "oidtree.h" #include "packfile.h" #include "pretty.h" -#include "object-store-ll.h" +#include "object-store.h" #include "read-cache-ll.h" #include "repo-settings.h" #include "repository.h" diff --git a/object-store-ll.h b/object-store-ll.h deleted file mode 100644 index cd3bd5bd99..0000000000 --- a/object-store-ll.h +++ /dev/null @@ -1,556 +0,0 @@ -#ifndef OBJECT_STORE_LL_H -#define OBJECT_STORE_LL_H - -#include "hashmap.h" -#include "object.h" -#include "list.h" -#include "thread-utils.h" -#include "oidset.h" - -struct oidmap; -struct oidtree; -struct strbuf; -struct repository; - -struct object_directory { - struct object_directory *next; - - /* - * Used to store the results of readdir(3) calls when we are OK - * sacrificing accuracy due to races for speed. That includes - * object existence with OBJECT_INFO_QUICK, as well as - * our search for unique abbreviated hashes. Don't use it for tasks - * requiring greater accuracy! - * - * Be sure to call odb_load_loose_cache() before using. - */ - uint32_t loose_objects_subdir_seen[8]; /* 256 bits */ - struct oidtree *loose_objects_cache; - - /* Map between object IDs for loose objects. */ - struct loose_object_map *loose_map; - - /* - * This is a temporary object store created by the tmp_objdir - * facility. Disable ref updates since the objects in the store - * might be discarded on rollback. - */ - int disable_ref_updates; - - /* - * This object store is ephemeral, so there is no need to fsync. - */ - int will_destroy; - - /* - * Path to the alternative object store. If this is a relative path, - * it is relative to the current working directory. - */ - char *path; -}; - -struct input_stream { - const void *(*read)(struct input_stream *, unsigned long *len); - void *data; - int is_finished; -}; - -void prepare_alt_odb(struct repository *r); -int has_alt_odb(struct repository *r); -char *compute_alternate_path(const char *path, struct strbuf *err); -struct object_directory *find_odb(struct repository *r, const char *obj_dir); -typedef int alt_odb_fn(struct object_directory *, void *); -int foreach_alt_odb(alt_odb_fn, void*); -typedef void alternate_ref_fn(const struct object_id *oid, void *); -void for_each_alternate_ref(alternate_ref_fn, void *); - -/* - * Add the directory to the on-disk alternates file; the new entry will also - * take effect in the current process. - */ -void add_to_alternates_file(const char *dir); - -/* - * Add the directory to the in-memory list of alternates (along with any - * recursive alternates it points to), but do not modify the on-disk alternates - * file. - */ -void add_to_alternates_memory(const char *dir); - -/* - * Replace the current writable object directory with the specified temporary - * object directory; returns the former primary object directory. - */ -struct object_directory *set_temporary_primary_odb(const char *dir, int will_destroy); - -/* - * Restore a previous ODB replaced by set_temporary_main_odb. - */ -void restore_primary_odb(struct object_directory *restore_odb, const char *old_path); - -/* - * Populate and return the loose object cache array corresponding to the - * given object ID. - */ -struct oidtree *odb_loose_cache(struct object_directory *odb, - const struct object_id *oid); - -/* Empty the loose object cache for the specified object directory. */ -void odb_clear_loose_cache(struct object_directory *odb); - -/* Clear and free the specified object directory */ -void free_object_directory(struct object_directory *odb); - -struct packed_git { - struct hashmap_entry packmap_ent; - struct packed_git *next; - struct list_head mru; - struct pack_window *windows; - off_t pack_size; - const void *index_data; - size_t index_size; - uint32_t num_objects; - size_t crc_offset; - struct oidset bad_objects; - int index_version; - time_t mtime; - int pack_fd; - int index; /* for builtin/pack-objects.c */ - unsigned pack_local:1, - pack_keep:1, - pack_keep_in_core:1, - freshened:1, - do_not_close:1, - pack_promisor:1, - multi_pack_index:1, - is_cruft:1; - unsigned char hash[GIT_MAX_RAWSZ]; - struct revindex_entry *revindex; - const uint32_t *revindex_data; - const uint32_t *revindex_map; - size_t revindex_size; - /* - * mtimes_map points at the beginning of the memory mapped region of - * this pack's corresponding .mtimes file, and mtimes_size is the size - * of that .mtimes file - */ - const uint32_t *mtimes_map; - size_t mtimes_size; - - /* repo denotes the repository this packfile belongs to */ - struct repository *repo; - - /* something like ".git/objects/pack/xxxxx.pack" */ - char pack_name[FLEX_ARRAY]; /* more */ -}; - -struct multi_pack_index; - -static inline int pack_map_entry_cmp(const void *cmp_data UNUSED, - const struct hashmap_entry *entry, - const struct hashmap_entry *entry2, - const void *keydata) -{ - const char *key = keydata; - const struct packed_git *pg1, *pg2; - - pg1 = container_of(entry, const struct packed_git, packmap_ent); - pg2 = container_of(entry2, const struct packed_git, packmap_ent); - - return strcmp(pg1->pack_name, key ? key : pg2->pack_name); -} - -struct raw_object_store { - /* - * Set of all object directories; the main directory is first (and - * cannot be NULL after initialization). Subsequent directories are - * alternates. - */ - struct object_directory *odb; - struct object_directory **odb_tail; - struct kh_odb_path_map *odb_by_path; - - int loaded_alternates; - - /* - * A list of alternate object directories loaded from the environment; - * this should not generally need to be accessed directly, but will - * populate the "odb" list when prepare_alt_odb() is run. - */ - char *alternate_db; - - /* - * Objects that should be substituted by other objects - * (see git-replace(1)). - */ - struct oidmap *replace_map; - unsigned replace_map_initialized : 1; - pthread_mutex_t replace_mutex; /* protect object replace functions */ - - struct commit_graph *commit_graph; - unsigned commit_graph_attempted : 1; /* if loading has been attempted */ - - /* - * private data - * - * should only be accessed directly by packfile.c and midx.c - */ - struct multi_pack_index *multi_pack_index; - - /* - * private data - * - * should only be accessed directly by packfile.c - */ - - struct packed_git *packed_git; - /* A most-recently-used ordered version of the packed_git list. */ - struct list_head packed_git_mru; - - struct { - struct packed_git **packs; - unsigned flags; - } kept_pack_cache; - - /* - * A map of packfiles to packed_git structs for tracking which - * packs have been loaded already. - */ - struct hashmap pack_map; - - /* - * A fast, rough count of the number of objects in the repository. - * These two fields are not meant for direct access. Use - * repo_approximate_object_count() instead. - */ - unsigned long approximate_object_count; - unsigned approximate_object_count_valid : 1; - - /* - * Whether packed_git has already been populated with this repository's - * packs. - */ - unsigned packed_git_initialized : 1; -}; - -struct raw_object_store *raw_object_store_new(void); -void raw_object_store_clear(struct raw_object_store *o); - -/* - * Create a temporary file rooted in the object database directory, or - * die on failure. The filename is taken from "pattern", which should have the - * usual "XXXXXX" trailer, and the resulting filename is written into the - * "template" buffer. Returns the open descriptor. - */ -int odb_mkstemp(struct strbuf *temp_filename, const char *pattern); - -/* - * Create a pack .keep file named "name" (which should generally be the output - * of odb_pack_name). Returns a file descriptor opened for writing, or -1 on - * error. - */ -int odb_pack_keep(const char *name); - -/* - * Put in `buf` the name of the file in the local object database that - * would be used to store a loose object with the specified oid. - */ -const char *loose_object_path(struct repository *r, struct strbuf *buf, - const struct object_id *oid); - -void *map_loose_object(struct repository *r, const struct object_id *oid, - unsigned long *size); - -void *repo_read_object_file(struct repository *r, - const struct object_id *oid, - enum object_type *type, - unsigned long *size); - -/* Read and unpack an object file into memory, write memory to an object file */ -int oid_object_info(struct repository *r, const struct object_id *, unsigned long *); - -void hash_object_file(const struct git_hash_algo *algo, const void *buf, - unsigned long len, enum object_type type, - struct object_id *oid); - -int write_object_file_flags(const void *buf, unsigned long len, - enum object_type type, struct object_id *oid, - struct object_id *comapt_oid_in, unsigned flags); -static inline int write_object_file(const void *buf, unsigned long len, - enum object_type type, struct object_id *oid) -{ - return write_object_file_flags(buf, len, type, oid, NULL, 0); -} - -int write_object_file_literally(const void *buf, unsigned long len, - const char *type, struct object_id *oid, - unsigned flags); -int stream_loose_object(struct input_stream *in_stream, size_t len, - struct object_id *oid); - -/* - * Add an object file to the in-memory object store, without writing it - * to disk. - * - * Callers are responsible for calling write_object_file to record the - * object in persistent storage before writing any other new objects - * that reference it. - */ -int pretend_object_file(void *, unsigned long, enum object_type, - struct object_id *oid); - -int force_object_loose(const struct object_id *oid, time_t mtime); - -struct object_info { - /* Request */ - enum object_type *typep; - unsigned long *sizep; - off_t *disk_sizep; - struct object_id *delta_base_oid; - struct strbuf *type_name; - void **contentp; - - /* Response */ - enum { - OI_CACHED, - OI_LOOSE, - OI_PACKED, - OI_DBCACHED - } whence; - union { - /* - * struct { - * ... Nothing to expose in this case - * } cached; - * struct { - * ... Nothing to expose in this case - * } loose; - */ - struct { - struct packed_git *pack; - off_t offset; - unsigned int is_delta; - } packed; - } u; -}; - -/* - * Initializer for a "struct object_info" that wants no items. You may - * also memset() the memory to all-zeroes. - */ -#define OBJECT_INFO_INIT { 0 } - -/* Invoke lookup_replace_object() on the given hash */ -#define OBJECT_INFO_LOOKUP_REPLACE 1 -/* Allow reading from a loose object file of unknown/bogus type */ -#define OBJECT_INFO_ALLOW_UNKNOWN_TYPE 2 -/* Do not retry packed storage after checking packed and loose storage */ -#define OBJECT_INFO_QUICK 8 -/* - * Do not attempt to fetch the object if missing (even if fetch_is_missing is - * nonzero). - */ -#define OBJECT_INFO_SKIP_FETCH_OBJECT 16 -/* - * This is meant for bulk prefetching of missing blobs in a partial - * clone. Implies OBJECT_INFO_SKIP_FETCH_OBJECT and OBJECT_INFO_QUICK - */ -#define OBJECT_INFO_FOR_PREFETCH (OBJECT_INFO_SKIP_FETCH_OBJECT | OBJECT_INFO_QUICK) - -/* Die if object corruption (not just an object being missing) was detected. */ -#define OBJECT_INFO_DIE_IF_CORRUPT 32 - -int oid_object_info_extended(struct repository *r, - const struct object_id *, - struct object_info *, unsigned flags); - -/* - * Open the loose object at path, check its hash, and return the contents, - * use the "oi" argument to assert things about the object, or e.g. populate its - * type, and size. If the object is a blob, then "contents" may return NULL, - * to allow streaming of large blobs. - * - * Returns 0 on success, negative on error (details may be written to stderr). - */ -int read_loose_object(const char *path, - const struct object_id *expected_oid, - struct object_id *real_oid, - void **contents, - struct object_info *oi); - -/* Retry packed storage after checking packed and loose storage */ -#define HAS_OBJECT_RECHECK_PACKED 1 - -/* - * Returns 1 if the object exists. This function will not lazily fetch objects - * in a partial clone. - */ -int has_object(struct repository *r, const struct object_id *oid, - unsigned flags); - -/* - * These macros and functions are deprecated. If checking existence for an - * object that is likely to be missing and/or whose absence is relatively - * inconsequential (or is consequential but the caller is prepared to handle - * it), use has_object(), which has better defaults (no lazy fetch in a partial - * clone and no rechecking of packed storage). In the unlikely event that a - * caller needs to assert existence of an object that it fully expects to - * exist, and wants to trigger a lazy fetch in a partial clone, use - * oid_object_info_extended() with a NULL struct object_info. - * - * These functions can be removed once all callers have migrated to - * has_object() and/or oid_object_info_extended(). - */ -int repo_has_object_file(struct repository *r, const struct object_id *oid); -int repo_has_object_file_with_flags(struct repository *r, - const struct object_id *oid, int flags); - -/* - * Return true iff an alternate object database has a loose object - * with the specified name. This function does not respect replace - * references. - */ -int has_loose_object_nonlocal(const struct object_id *); - -int has_loose_object(const struct object_id *); - -/** - * format_object_header() is a thin wrapper around s xsnprintf() that - * writes the initial " " part of the loose object - * header. It returns the size that snprintf() returns + 1. - */ -int format_object_header(char *str, size_t size, enum object_type type, - size_t objsize); - -void assert_oid_type(const struct object_id *oid, enum object_type expect); - -/* - * Enabling the object read lock allows multiple threads to safely call the - * following functions in parallel: repo_read_object_file(), - * read_object_with_reference(), oid_object_info() and oid_object_info_extended(). - * - * obj_read_lock() and obj_read_unlock() may also be used to protect other - * section which cannot execute in parallel with object reading. Since the used - * lock is a recursive mutex, these sections can even contain calls to object - * reading functions. However, beware that in these cases zlib inflation won't - * be performed in parallel, losing performance. - * - * TODO: oid_object_info_extended()'s call stack has a recursive behavior. If - * any of its callees end up calling it, this recursive call won't benefit from - * parallel inflation. - */ -void enable_obj_read_lock(void); -void disable_obj_read_lock(void); - -extern int obj_read_use_lock; -extern pthread_mutex_t obj_read_mutex; - -static inline void obj_read_lock(void) -{ - if(obj_read_use_lock) - pthread_mutex_lock(&obj_read_mutex); -} - -static inline void obj_read_unlock(void) -{ - if(obj_read_use_lock) - pthread_mutex_unlock(&obj_read_mutex); -} - -/* - * Iterate over the files in the loose-object parts of the object - * directory "path", triggering the following callbacks: - * - * - loose_object is called for each loose object we find. - * - * - loose_cruft is called for any files that do not appear to be - * loose objects. Note that we only look in the loose object - * directories "objects/[0-9a-f]{2}/", so we will not report - * "objects/foobar" as cruft. - * - * - loose_subdir is called for each top-level hashed subdirectory - * of the object directory (e.g., "$OBJDIR/f0"). It is called - * after the objects in the directory are processed. - * - * Any callback that is NULL will be ignored. Callbacks returning non-zero - * will end the iteration. - * - * In the "buf" variant, "path" is a strbuf which will also be used as a - * scratch buffer, but restored to its original contents before - * the function returns. - */ -typedef int each_loose_object_fn(const struct object_id *oid, - const char *path, - void *data); -typedef int each_loose_cruft_fn(const char *basename, - const char *path, - void *data); -typedef int each_loose_subdir_fn(unsigned int nr, - const char *path, - void *data); -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); -int for_each_loose_file_in_objdir(const char *path, - each_loose_object_fn obj_cb, - each_loose_cruft_fn cruft_cb, - each_loose_subdir_fn subdir_cb, - void *data); -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); - -/* Flags for for_each_*_object() below. */ -enum for_each_object_flags { - /* Iterate only over local objects, not alternates. */ - FOR_EACH_OBJECT_LOCAL_ONLY = (1<<0), - - /* Only iterate over packs obtained from the promisor remote. */ - FOR_EACH_OBJECT_PROMISOR_ONLY = (1<<1), - - /* - * Visit objects within a pack in packfile order rather than .idx order - */ - FOR_EACH_OBJECT_PACK_ORDER = (1<<2), - - /* Only iterate over packs that are not marked as kept in-core. */ - FOR_EACH_OBJECT_SKIP_IN_CORE_KEPT_PACKS = (1<<3), - - /* Only iterate over packs that do not have .keep files. */ - FOR_EACH_OBJECT_SKIP_ON_DISK_KEPT_PACKS = (1<<4), -}; - -/* - * Iterate over all accessible loose objects without respect to - * reachability. By default, this includes both local and alternate objects. - * The order in which objects are visited is unspecified. - * - * Any flags specific to packs are ignored. - */ -int for_each_loose_object(each_loose_object_fn, void *, - enum for_each_object_flags flags); - -/* - * Iterate over all accessible packed objects without respect to reachability. - * By default, this includes both local and alternate packs. - * - * Note that some objects may appear twice if they are found in multiple packs. - * Each pack is visited in an unspecified order. By default, objects within a - * pack are visited in pack-idx order (i.e., sorted by oid). - */ -typedef int each_packed_object_fn(const struct object_id *oid, - struct packed_git *pack, - uint32_t pos, - void *data); -int for_each_object_in_pack(struct packed_git *p, - each_packed_object_fn, void *data, - enum for_each_object_flags flags); -int for_each_packed_object(struct repository *repo, each_packed_object_fn cb, - void *data, enum for_each_object_flags flags); - -#endif /* OBJECT_STORE_LL_H */ diff --git a/object-store.c b/object-store.c new file mode 100644 index 0000000000..6ab50d25d3 --- /dev/null +++ b/object-store.c @@ -0,0 +1,1050 @@ +#define USE_THE_REPOSITORY_VARIABLE + +#include "git-compat-util.h" +#include "abspath.h" +#include "commit-graph.h" +#include "config.h" +#include "dir.h" +#include "environment.h" +#include "gettext.h" +#include "hex.h" +#include "khash.h" +#include "lockfile.h" +#include "loose.h" +#include "object-file-convert.h" +#include "object-file.h" +#include "object-store.h" +#include "packfile.h" +#include "path.h" +#include "promisor-remote.h" +#include "quote.h" +#include "replace-object.h" +#include "run-command.h" +#include "setup.h" +#include "strbuf.h" +#include "strvec.h" +#include "submodule.h" +#include "write-or-die.h" + +KHASH_INIT(odb_path_map, const char * /* key: odb_path */, + struct object_directory *, 1, fspathhash, fspatheq) + +/* + * 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). + */ +struct cached_object_entry { + struct object_id oid; + struct cached_object { + enum object_type type; + const void *buf; + unsigned long size; + } value; +}; + +static const struct cached_object *find_cached_object(struct raw_object_store *object_store, + const struct object_id *oid) +{ + static const struct cached_object empty_tree = { + .type = OBJ_TREE, + .buf = "", + }; + const struct cached_object_entry *co = object_store->cached_objects; + + for (size_t i = 0; i < object_store->cached_object_nr; i++, co++) + if (oideq(&co->oid, oid)) + return &co->value; + + if (oid->algo && oideq(oid, hash_algos[oid->algo].empty_tree)) + return &empty_tree; + + return NULL; +} + +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; + repo_git_path_replace(the_repository, 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 */ + repo_git_path_replace(the_repository, temp_filename, "objects/%s", pattern); + safe_create_leading_directories(the_repository, 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(the_repository, name); + return open(name, O_RDWR|O_CREAT|O_EXCL, 0600); +} + +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 = repo_git_path(the_repository, "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; +} + +static void free_object_directory(struct object_directory *odb) +{ + free(odb->path); + odb_clear_loose_cache(odb); + loose_object_map_clear(&odb->loose_map); + free(odb); +} + +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; +} + +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(r->objects, 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(the_repository, &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(struct repository *repo, + void *buf, unsigned long len, enum object_type type, + struct object_id *oid) +{ + struct cached_object_entry *co; + char *co_buf; + + hash_object_file(repo->hash_algo, buf, len, type, oid); + if (repo_has_object_file_with_flags(repo, oid, OBJECT_INFO_QUICK | OBJECT_INFO_SKIP_FETCH_OBJECT) || + find_cached_object(repo->objects, oid)) + return 0; + + ALLOC_GROW(repo->objects->cached_objects, + repo->objects->cached_object_nr + 1, repo->objects->cached_object_alloc); + co = &repo->objects->cached_objects[repo->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. */ + } +} + +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); +} + +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)); +} + +struct raw_object_store *raw_object_store_new(void) +{ + struct raw_object_store *o = xmalloc(sizeof(*o)); + + memset(o, 0, sizeof(*o)); + INIT_LIST_HEAD(&o->packed_git_mru); + hashmap_init(&o->pack_map, pack_map_entry_cmp, NULL, 0); + pthread_mutex_init(&o->replace_mutex, NULL); + return o; +} + +static void free_object_directories(struct raw_object_store *o) +{ + while (o->odb) { + struct object_directory *next; + + next = o->odb->next; + free_object_directory(o->odb); + o->odb = next; + } + kh_destroy_odb_path_map(o->odb_by_path); + o->odb_by_path = NULL; +} + +void raw_object_store_clear(struct raw_object_store *o) +{ + FREE_AND_NULL(o->alternate_db); + + oidmap_free(o->replace_map, 1); + FREE_AND_NULL(o->replace_map); + pthread_mutex_destroy(&o->replace_mutex); + + free_commit_graph(o->commit_graph); + o->commit_graph = NULL; + o->commit_graph_attempted = 0; + + free_object_directories(o); + o->odb_tail = NULL; + o->loaded_alternates = 0; + + for (size_t i = 0; i < o->cached_object_nr; i++) + free((char *) o->cached_objects[i].value.buf); + FREE_AND_NULL(o->cached_objects); + + INIT_LIST_HEAD(&o->packed_git_mru); + close_object_store(o); + + /* + * `close_object_store()` only closes the packfiles, but doesn't free + * them. We thus have to do this manually. + */ + for (struct packed_git *p = o->packed_git, *next; p; p = next) { + next = p->next; + free(p); + } + o->packed_git = NULL; + + hashmap_clear(&o->pack_map); +} diff --git a/object-store.h b/object-store.h index 1b3e3d7d01..46961dc954 100644 --- a/object-store.h +++ b/object-store.h @@ -1,11 +1,517 @@ #ifndef OBJECT_STORE_H #define OBJECT_STORE_H -#include "khash.h" -#include "dir.h" -#include "object-store-ll.h" +#include "hashmap.h" +#include "object.h" +#include "list.h" +#include "oidset.h" +#include "thread-utils.h" -KHASH_INIT(odb_path_map, const char * /* key: odb_path */, - struct object_directory *, 1, fspathhash, fspatheq) +struct oidmap; +struct oidtree; +struct strbuf; +struct repository; + +struct object_directory { + struct object_directory *next; + + /* + * Used to store the results of readdir(3) calls when we are OK + * sacrificing accuracy due to races for speed. That includes + * object existence with OBJECT_INFO_QUICK, as well as + * our search for unique abbreviated hashes. Don't use it for tasks + * requiring greater accuracy! + * + * Be sure to call odb_load_loose_cache() before using. + */ + uint32_t loose_objects_subdir_seen[8]; /* 256 bits */ + struct oidtree *loose_objects_cache; + + /* Map between object IDs for loose objects. */ + struct loose_object_map *loose_map; + + /* + * This is a temporary object store created by the tmp_objdir + * facility. Disable ref updates since the objects in the store + * might be discarded on rollback. + */ + int disable_ref_updates; + + /* + * This object store is ephemeral, so there is no need to fsync. + */ + int will_destroy; + + /* + * Path to the alternative object store. If this is a relative path, + * it is relative to the current working directory. + */ + char *path; +}; + +void prepare_alt_odb(struct repository *r); +int has_alt_odb(struct repository *r); +char *compute_alternate_path(const char *path, struct strbuf *err); +struct object_directory *find_odb(struct repository *r, const char *obj_dir); +typedef int alt_odb_fn(struct object_directory *, void *); +int foreach_alt_odb(alt_odb_fn, void*); +typedef void alternate_ref_fn(const struct object_id *oid, void *); +void for_each_alternate_ref(alternate_ref_fn, void *); + +/* + * Add the directory to the on-disk alternates file; the new entry will also + * take effect in the current process. + */ +void add_to_alternates_file(const char *dir); + +/* + * Add the directory to the in-memory list of alternates (along with any + * recursive alternates it points to), but do not modify the on-disk alternates + * file. + */ +void add_to_alternates_memory(const char *dir); + +/* + * Replace the current writable object directory with the specified temporary + * object directory; returns the former primary object directory. + */ +struct object_directory *set_temporary_primary_odb(const char *dir, int will_destroy); + +/* + * Restore a previous ODB replaced by set_temporary_main_odb. + */ +void restore_primary_odb(struct object_directory *restore_odb, const char *old_path); + +/* + * Populate and return the loose object cache array corresponding to the + * given object ID. + */ +struct oidtree *odb_loose_cache(struct object_directory *odb, + const struct object_id *oid); + +/* Empty the loose object cache for the specified object directory. */ +void odb_clear_loose_cache(struct object_directory *odb); + +struct packed_git { + struct hashmap_entry packmap_ent; + struct packed_git *next; + struct list_head mru; + struct pack_window *windows; + off_t pack_size; + const void *index_data; + size_t index_size; + uint32_t num_objects; + size_t crc_offset; + struct oidset bad_objects; + int index_version; + time_t mtime; + int pack_fd; + int index; /* for builtin/pack-objects.c */ + unsigned pack_local:1, + pack_keep:1, + pack_keep_in_core:1, + freshened:1, + do_not_close:1, + pack_promisor:1, + multi_pack_index:1, + is_cruft:1; + unsigned char hash[GIT_MAX_RAWSZ]; + struct revindex_entry *revindex; + const uint32_t *revindex_data; + const uint32_t *revindex_map; + size_t revindex_size; + /* + * mtimes_map points at the beginning of the memory mapped region of + * this pack's corresponding .mtimes file, and mtimes_size is the size + * of that .mtimes file + */ + const uint32_t *mtimes_map; + size_t mtimes_size; + + /* repo denotes the repository this packfile belongs to */ + struct repository *repo; + + /* something like ".git/objects/pack/xxxxx.pack" */ + char pack_name[FLEX_ARRAY]; /* more */ +}; + +struct multi_pack_index; + +static inline int pack_map_entry_cmp(const void *cmp_data UNUSED, + const struct hashmap_entry *entry, + const struct hashmap_entry *entry2, + const void *keydata) +{ + const char *key = keydata; + const struct packed_git *pg1, *pg2; + + pg1 = container_of(entry, const struct packed_git, packmap_ent); + pg2 = container_of(entry2, const struct packed_git, packmap_ent); + + return strcmp(pg1->pack_name, key ? key : pg2->pack_name); +} + +struct cached_object_entry; + +struct raw_object_store { + /* + * Set of all object directories; the main directory is first (and + * cannot be NULL after initialization). Subsequent directories are + * alternates. + */ + struct object_directory *odb; + struct object_directory **odb_tail; + struct kh_odb_path_map *odb_by_path; + + int loaded_alternates; + + /* + * A list of alternate object directories loaded from the environment; + * this should not generally need to be accessed directly, but will + * populate the "odb" list when prepare_alt_odb() is run. + */ + char *alternate_db; + + /* + * Objects that should be substituted by other objects + * (see git-replace(1)). + */ + struct oidmap *replace_map; + unsigned replace_map_initialized : 1; + pthread_mutex_t replace_mutex; /* protect object replace functions */ + + struct commit_graph *commit_graph; + unsigned commit_graph_attempted : 1; /* if loading has been attempted */ + + /* + * private data + * + * should only be accessed directly by packfile.c and midx.c + */ + struct multi_pack_index *multi_pack_index; + + /* + * private data + * + * should only be accessed directly by packfile.c + */ + + struct packed_git *packed_git; + /* A most-recently-used ordered version of the packed_git list. */ + struct list_head packed_git_mru; + + struct { + struct packed_git **packs; + unsigned flags; + } kept_pack_cache; + + /* + * 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). + */ + struct cached_object_entry *cached_objects; + size_t cached_object_nr, cached_object_alloc; + + /* + * A map of packfiles to packed_git structs for tracking which + * packs have been loaded already. + */ + struct hashmap pack_map; + + /* + * A fast, rough count of the number of objects in the repository. + * These two fields are not meant for direct access. Use + * repo_approximate_object_count() instead. + */ + unsigned long approximate_object_count; + unsigned approximate_object_count_valid : 1; + + /* + * Whether packed_git has already been populated with this repository's + * packs. + */ + unsigned packed_git_initialized : 1; +}; + +struct raw_object_store *raw_object_store_new(void); +void raw_object_store_clear(struct raw_object_store *o); + +/* + * Create a temporary file rooted in the object database directory, or + * die on failure. The filename is taken from "pattern", which should have the + * usual "XXXXXX" trailer, and the resulting filename is written into the + * "template" buffer. Returns the open descriptor. + */ +int odb_mkstemp(struct strbuf *temp_filename, const char *pattern); + +/* + * Create a pack .keep file named "name" (which should generally be the output + * of odb_pack_name). Returns a file descriptor opened for writing, or -1 on + * error. + */ +int odb_pack_keep(const char *name); + +/* + * Put in `buf` the name of the file in the local object database that + * would be used to store a loose object with the specified oid. + */ +const char *loose_object_path(struct repository *r, struct strbuf *buf, + const struct object_id *oid); + +void *map_loose_object(struct repository *r, const struct object_id *oid, + unsigned long *size); + +void *repo_read_object_file(struct repository *r, + const struct object_id *oid, + enum object_type *type, + unsigned long *size); + +/* Read and unpack an object file into memory, write memory to an object file */ +int oid_object_info(struct repository *r, const struct object_id *, unsigned long *); + +void hash_object_file(const struct git_hash_algo *algo, const void *buf, + unsigned long len, enum object_type type, + struct object_id *oid); + +/* + * Add an object file to the in-memory object store, without writing it + * to disk. + * + * Callers are responsible for calling write_object_file to record the + * object in persistent storage before writing any other new objects + * that reference it. + */ +int pretend_object_file(struct repository *repo, + void *buf, unsigned long len, enum object_type type, + struct object_id *oid); + +struct object_info { + /* Request */ + enum object_type *typep; + unsigned long *sizep; + off_t *disk_sizep; + struct object_id *delta_base_oid; + struct strbuf *type_name; + void **contentp; + + /* Response */ + enum { + OI_CACHED, + OI_LOOSE, + OI_PACKED, + OI_DBCACHED + } whence; + union { + /* + * struct { + * ... Nothing to expose in this case + * } cached; + * struct { + * ... Nothing to expose in this case + * } loose; + */ + struct { + struct packed_git *pack; + off_t offset; + unsigned int is_delta; + } packed; + } u; +}; + +/* + * Initializer for a "struct object_info" that wants no items. You may + * also memset() the memory to all-zeroes. + */ +#define OBJECT_INFO_INIT { 0 } + +/* Invoke lookup_replace_object() on the given hash */ +#define OBJECT_INFO_LOOKUP_REPLACE 1 +/* Allow reading from a loose object file of unknown/bogus type */ +#define OBJECT_INFO_ALLOW_UNKNOWN_TYPE 2 +/* Do not retry packed storage after checking packed and loose storage */ +#define OBJECT_INFO_QUICK 8 +/* + * Do not attempt to fetch the object if missing (even if fetch_is_missing is + * nonzero). + */ +#define OBJECT_INFO_SKIP_FETCH_OBJECT 16 +/* + * This is meant for bulk prefetching of missing blobs in a partial + * clone. Implies OBJECT_INFO_SKIP_FETCH_OBJECT and OBJECT_INFO_QUICK + */ +#define OBJECT_INFO_FOR_PREFETCH (OBJECT_INFO_SKIP_FETCH_OBJECT | OBJECT_INFO_QUICK) + +/* Die if object corruption (not just an object being missing) was detected. */ +#define OBJECT_INFO_DIE_IF_CORRUPT 32 + +int oid_object_info_extended(struct repository *r, + const struct object_id *, + struct object_info *, unsigned flags); + +/* Retry packed storage after checking packed and loose storage */ +#define HAS_OBJECT_RECHECK_PACKED 1 + +/* + * Returns 1 if the object exists. This function will not lazily fetch objects + * in a partial clone. + */ +int has_object(struct repository *r, const struct object_id *oid, + unsigned flags); + +/* + * These macros and functions are deprecated. If checking existence for an + * object that is likely to be missing and/or whose absence is relatively + * inconsequential (or is consequential but the caller is prepared to handle + * it), use has_object(), which has better defaults (no lazy fetch in a partial + * clone and no rechecking of packed storage). In the unlikely event that a + * caller needs to assert existence of an object that it fully expects to + * exist, and wants to trigger a lazy fetch in a partial clone, use + * oid_object_info_extended() with a NULL struct object_info. + * + * These functions can be removed once all callers have migrated to + * has_object() and/or oid_object_info_extended(). + */ +int repo_has_object_file(struct repository *r, const struct object_id *oid); +int repo_has_object_file_with_flags(struct repository *r, + const struct object_id *oid, int flags); + +void assert_oid_type(const struct object_id *oid, enum object_type expect); + +/* + * Enabling the object read lock allows multiple threads to safely call the + * following functions in parallel: repo_read_object_file(), + * read_object_with_reference(), oid_object_info() and oid_object_info_extended(). + * + * obj_read_lock() and obj_read_unlock() may also be used to protect other + * section which cannot execute in parallel with object reading. Since the used + * lock is a recursive mutex, these sections can even contain calls to object + * reading functions. However, beware that in these cases zlib inflation won't + * be performed in parallel, losing performance. + * + * TODO: oid_object_info_extended()'s call stack has a recursive behavior. If + * any of its callees end up calling it, this recursive call won't benefit from + * parallel inflation. + */ +void enable_obj_read_lock(void); +void disable_obj_read_lock(void); + +extern int obj_read_use_lock; +extern pthread_mutex_t obj_read_mutex; + +static inline void obj_read_lock(void) +{ + if(obj_read_use_lock) + pthread_mutex_lock(&obj_read_mutex); +} + +static inline void obj_read_unlock(void) +{ + if(obj_read_use_lock) + pthread_mutex_unlock(&obj_read_mutex); +} + +/* + * Iterate over the files in the loose-object parts of the object + * directory "path", triggering the following callbacks: + * + * - loose_object is called for each loose object we find. + * + * - loose_cruft is called for any files that do not appear to be + * loose objects. Note that we only look in the loose object + * directories "objects/[0-9a-f]{2}/", so we will not report + * "objects/foobar" as cruft. + * + * - loose_subdir is called for each top-level hashed subdirectory + * of the object directory (e.g., "$OBJDIR/f0"). It is called + * after the objects in the directory are processed. + * + * Any callback that is NULL will be ignored. Callbacks returning non-zero + * will end the iteration. + * + * In the "buf" variant, "path" is a strbuf which will also be used as a + * scratch buffer, but restored to its original contents before + * the function returns. + */ +typedef int each_loose_object_fn(const struct object_id *oid, + const char *path, + void *data); +typedef int each_loose_cruft_fn(const char *basename, + const char *path, + void *data); +typedef int each_loose_subdir_fn(unsigned int nr, + const char *path, + void *data); +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); +int for_each_loose_file_in_objdir(const char *path, + each_loose_object_fn obj_cb, + each_loose_cruft_fn cruft_cb, + each_loose_subdir_fn subdir_cb, + void *data); +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); + +/* Flags for for_each_*_object() below. */ +enum for_each_object_flags { + /* Iterate only over local objects, not alternates. */ + FOR_EACH_OBJECT_LOCAL_ONLY = (1<<0), + + /* Only iterate over packs obtained from the promisor remote. */ + FOR_EACH_OBJECT_PROMISOR_ONLY = (1<<1), + + /* + * Visit objects within a pack in packfile order rather than .idx order + */ + FOR_EACH_OBJECT_PACK_ORDER = (1<<2), + + /* Only iterate over packs that are not marked as kept in-core. */ + FOR_EACH_OBJECT_SKIP_IN_CORE_KEPT_PACKS = (1<<3), + + /* Only iterate over packs that do not have .keep files. */ + FOR_EACH_OBJECT_SKIP_ON_DISK_KEPT_PACKS = (1<<4), +}; + +/* + * Iterate over all accessible loose objects without respect to + * reachability. By default, this includes both local and alternate objects. + * The order in which objects are visited is unspecified. + * + * Any flags specific to packs are ignored. + */ +int for_each_loose_object(each_loose_object_fn, void *, + enum for_each_object_flags flags); + +/* + * Iterate over all accessible packed objects without respect to reachability. + * By default, this includes both local and alternate packs. + * + * Note that some objects may appear twice if they are found in multiple packs. + * Each pack is visited in an unspecified order. By default, objects within a + * pack are visited in pack-idx order (i.e., sorted by oid). + */ +typedef int each_packed_object_fn(const struct object_id *oid, + struct packed_git *pack, + uint32_t pos, + void *data); +int for_each_object_in_pack(struct packed_git *p, + each_packed_object_fn, void *data, + enum for_each_object_flags flags); +int for_each_packed_object(struct repository *repo, each_packed_object_fn cb, + void *data, enum for_each_object_flags flags); + +void *read_object_with_reference(struct repository *r, + const struct object_id *oid, + enum object_type required_type, + unsigned long *size, + struct object_id *oid_ret); #endif /* OBJECT_STORE_H */ diff --git a/object.c b/object.c index d054e7f0d0..3b15469139 100644 --- a/object.c +++ b/object.c @@ -6,16 +6,13 @@ #include "object.h" #include "replace-object.h" #include "object-file.h" -#include "object-store.h" #include "blob.h" #include "statinfo.h" #include "tree.h" #include "commit.h" #include "tag.h" #include "alloc.h" -#include "packfile.h" #include "commit-graph.h" -#include "loose.h" unsigned int get_max_object_index(const struct repository *repo) { @@ -534,70 +531,6 @@ struct parsed_object_pool *parsed_object_pool_new(struct repository *repo) return o; } -struct raw_object_store *raw_object_store_new(void) -{ - struct raw_object_store *o = xmalloc(sizeof(*o)); - - memset(o, 0, sizeof(*o)); - INIT_LIST_HEAD(&o->packed_git_mru); - hashmap_init(&o->pack_map, pack_map_entry_cmp, NULL, 0); - pthread_mutex_init(&o->replace_mutex, NULL); - return o; -} - -void free_object_directory(struct object_directory *odb) -{ - free(odb->path); - odb_clear_loose_cache(odb); - loose_object_map_clear(&odb->loose_map); - free(odb); -} - -static void free_object_directories(struct raw_object_store *o) -{ - while (o->odb) { - struct object_directory *next; - - next = o->odb->next; - free_object_directory(o->odb); - o->odb = next; - } - kh_destroy_odb_path_map(o->odb_by_path); - o->odb_by_path = NULL; -} - -void raw_object_store_clear(struct raw_object_store *o) -{ - FREE_AND_NULL(o->alternate_db); - - oidmap_free(o->replace_map, 1); - FREE_AND_NULL(o->replace_map); - pthread_mutex_destroy(&o->replace_mutex); - - free_commit_graph(o->commit_graph); - o->commit_graph = NULL; - o->commit_graph_attempted = 0; - - free_object_directories(o); - o->odb_tail = NULL; - o->loaded_alternates = 0; - - INIT_LIST_HEAD(&o->packed_git_mru); - close_object_store(o); - - /* - * `close_object_store()` only closes the packfiles, but doesn't free - * them. We thus have to do this manually. - */ - for (struct packed_git *p = o->packed_git, *next; p; p = next) { - next = p->next; - free(p); - } - o->packed_git = NULL; - - hashmap_clear(&o->pack_map); -} - void parsed_object_pool_reset_commit_grafts(struct parsed_object_pool *o) { for (int i = 0; i < o->grafts_nr; i++) { diff --git a/oss-fuzz/fuzz-pack-idx.c b/oss-fuzz/fuzz-pack-idx.c index 3e190214d1..609a343ee3 100644 --- a/oss-fuzz/fuzz-pack-idx.c +++ b/oss-fuzz/fuzz-pack-idx.c @@ -1,5 +1,5 @@ #include "git-compat-util.h" -#include "object-store-ll.h" +#include "object-store.h" #include "packfile.h" int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size); diff --git a/pack-bitmap-write.c b/pack-bitmap-write.c index 02051c6e71..7f400ee012 100644 --- a/pack-bitmap-write.c +++ b/pack-bitmap-write.c @@ -4,7 +4,7 @@ #include "environment.h" #include "gettext.h" #include "hex.h" -#include "object-store-ll.h" +#include "object-store.h" #include "commit.h" #include "diff.h" #include "revision.h" diff --git a/pack-bitmap.c b/pack-bitmap.c index 5299f49d59..b9f1d86604 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -17,8 +17,7 @@ #include "packfile.h" #include "repository.h" #include "trace2.h" -#include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "list-objects-filter-options.h" #include "midx.h" #include "config.h" diff --git a/pack-check.c b/pack-check.c index 95dcbbe985..874897d6cb 100644 --- a/pack-check.c +++ b/pack-check.c @@ -8,7 +8,7 @@ #include "progress.h" #include "packfile.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" struct idx_entry { off_t offset; diff --git a/pack-mtimes.c b/pack-mtimes.c index cdf30b8d2b..20900ca88d 100644 --- a/pack-mtimes.c +++ b/pack-mtimes.c @@ -1,8 +1,7 @@ #include "git-compat-util.h" #include "gettext.h" #include "pack-mtimes.h" -#include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "packfile.h" #include "strbuf.h" diff --git a/pack-objects.h b/pack-objects.h index d73e3843c9..d1c4ae7f9b 100644 --- a/pack-objects.h +++ b/pack-objects.h @@ -1,7 +1,7 @@ #ifndef PACK_OBJECTS_H #define PACK_OBJECTS_H -#include "object-store-ll.h" +#include "object-store.h" #include "thread-utils.h" #include "pack.h" diff --git a/pack-revindex.c b/pack-revindex.c index f035a33a5a..ffcde48870 100644 --- a/pack-revindex.c +++ b/pack-revindex.c @@ -1,8 +1,7 @@ #include "git-compat-util.h" #include "gettext.h" #include "pack-revindex.h" -#include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "packfile.h" #include "strbuf.h" #include "trace2.h" diff --git a/packfile.c b/packfile.c index 9d09f8bc72..d91016f1c7 100644 --- a/packfile.c +++ b/packfile.c @@ -19,7 +19,7 @@ #include "tree-walk.h" #include "tree.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "midx.h" #include "commit-graph.h" #include "pack-revindex.h" diff --git a/path.c b/path.c index 910756c8b3..4505bb78e8 100644 --- a/path.c +++ b/path.c @@ -15,7 +15,7 @@ #include "submodule-config.h" #include "path.h" #include "packfile.h" -#include "object-store-ll.h" +#include "object-store.h" #include "lockfile.h" #include "exec-cmd.h" @@ -902,6 +902,115 @@ void safe_create_dir(struct repository *repo, const char *dir, int share) die(_("Could not make %s writable by group"), dir); } +int safe_create_dir_in_gitdir(struct repository *repo, 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(repo, path); +} + +static enum scld_error safe_create_leading_directories_1(struct repository *repo, + char *path) +{ + 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 (repo && adjust_shared_perm(repo, path)) { + ret = SCLD_PERMS; + } + *slash = slash_character; + } + return ret; +} + +enum scld_error safe_create_leading_directories(struct repository *repo, + char *path) +{ + return safe_create_leading_directories_1(repo, path); +} + +enum scld_error safe_create_leading_directories_no_share(char *path) +{ + return safe_create_leading_directories_1(NULL, path); +} + +enum scld_error safe_create_leading_directories_const(struct repository *repo, + 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(repo, buf); + + save_errno = errno; + free(buf); + errno = save_errno; + return result; +} + static int have_same_root(const char *path1, const char *path2) { int is_abs1, is_abs2; diff --git a/path.h b/path.h index 65fe968a13..fd1a194b06 100644 --- a/path.h +++ b/path.h @@ -221,6 +221,51 @@ char *xdg_cache_home(const char *filename); */ void safe_create_dir(struct repository *repo, const char *dir, int share); +/* + * Similar to `safe_create_dir()`, but with two differences: + * + * - It knows to resolve gitlink files for symlinked worktrees. + * + * - It always adjusts shared permissions. + * + * Returns a negative erorr code on error, 0 on success. + */ +int safe_create_dir_in_gitdir(struct repository *repo, const char *path); + +/* + * Create the directory containing the named path, using care to be + * somewhat safe against races. Return one of the scld_error values to + * indicate success/failure. On error, set errno to describe the + * problem. + * + * SCLD_VANISHED indicates that one of the ancestor directories of the + * path existed at one point during the function call and then + * suddenly vanished, probably because another process pruned the + * directory while we were working. To be robust against this kind of + * race, callers might want to try invoking the function again when it + * returns SCLD_VANISHED. + * + * safe_create_leading_directories() temporarily changes path while it + * is working but restores it before returning. + * safe_create_leading_directories_const() doesn't modify path, even + * temporarily. Both these variants adjust the permissions of the + * created directories to honor core.sharedRepository, so they are best + * suited for files inside the git dir. For working tree files, use + * safe_create_leading_directories_no_share() instead, as it ignores + * the core.sharedRepository setting. + */ +enum scld_error { + SCLD_OK = 0, + SCLD_FAILED = -1, + SCLD_PERMS = -2, + SCLD_EXISTS = -3, + SCLD_VANISHED = -4 +}; +enum scld_error safe_create_leading_directories(struct repository *repo, char *path); +enum scld_error safe_create_leading_directories_const(struct repository *repo, + const char *path); +enum scld_error safe_create_leading_directories_no_share(char *path); + # ifdef USE_THE_REPOSITORY_VARIABLE # include "strbuf.h" # include "repository.h" diff --git a/promisor-remote.c b/promisor-remote.c index 5801ebfd9b..9d058586df 100644 --- a/promisor-remote.c +++ b/promisor-remote.c @@ -3,7 +3,7 @@ #include "git-compat-util.h" #include "gettext.h" #include "hex.h" -#include "object-store-ll.h" +#include "object-store.h" #include "promisor-remote.h" #include "config.h" #include "trace2.h" diff --git a/protocol-caps.c b/protocol-caps.c index 855f279c2f..9b8db37a21 100644 --- a/protocol-caps.c +++ b/protocol-caps.c @@ -6,7 +6,7 @@ #include "hash.h" #include "hex.h" #include "object.h" -#include "object-store-ll.h" +#include "object-store.h" #include "repository.h" #include "string-list.h" #include "strbuf.h" diff --git a/prune-packed.c b/prune-packed.c index 7dad2fc0c1..c1d95a519d 100644 --- a/prune-packed.c +++ b/prune-packed.c @@ -2,7 +2,7 @@ #include "git-compat-util.h" #include "gettext.h" -#include "object-store-ll.h" +#include "object-store.h" #include "packfile.h" #include "progress.h" #include "prune-packed.h" diff --git a/reachable.c b/reachable.c index 299e129249..e5f56f4018 100644 --- a/reachable.c +++ b/reachable.c @@ -14,7 +14,7 @@ #include "list-objects.h" #include "packfile.h" #include "worktree.h" -#include "object-store-ll.h" +#include "object-store.h" #include "pack-bitmap.h" #include "pack-mtimes.h" #include "config.h" diff --git a/read-cache.c b/read-cache.c index 4cdc7bb661..73f83a7e7a 100644 --- a/read-cache.c +++ b/read-cache.c @@ -20,7 +20,7 @@ #include "refs.h" #include "dir.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "oid-array.h" #include "tree.h" #include "commit.h" @@ -706,11 +706,11 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st, int intent_only = flags & ADD_CACHE_INTENT; int add_option = (ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE| (intent_only ? ADD_CACHE_NEW_ONLY : 0)); - unsigned hash_flags = pretend ? 0 : HASH_WRITE_OBJECT; + unsigned hash_flags = pretend ? 0 : INDEX_WRITE_OBJECT; struct object_id oid; if (flags & ADD_CACHE_RENORMALIZE) - hash_flags |= HASH_RENORMALIZE; + hash_flags |= INDEX_RENORMALIZE; if (!S_ISREG(st_mode) && !S_ISLNK(st_mode) && !S_ISDIR(st_mode)) return error(_("%s: can only add regular files, symbolic links or git-directories"), path); diff --git a/ref-filter.c b/ref-filter.c index 6da8d4c03b..7a274633cf 100644 --- a/ref-filter.c +++ b/ref-filter.c @@ -12,7 +12,7 @@ #include "refs.h" #include "wildmatch.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "oid-array.h" #include "repo-settings.h" #include "repository.h" diff --git a/reflog.c b/reflog.c index 642b162ef7..12f7a02e34 100644 --- a/reflog.c +++ b/reflog.c @@ -4,8 +4,8 @@ #include "git-compat-util.h" #include "config.h" #include "gettext.h" -#include "object-store-ll.h" #include "parse-options.h" +#include "object-store.h" #include "reflog.h" #include "refs.h" #include "revision.h" diff --git a/refs.c b/refs.c index 6720c3da28..6559db3789 100644 --- a/refs.c +++ b/refs.c @@ -19,7 +19,7 @@ #include "run-command.h" #include "hook.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "object.h" #include "path.h" #include "submodule.h" diff --git a/refs/files-backend.c b/refs/files-backend.c index 5057dd02ed..4d1f65a57a 100644 --- a/refs/files-backend.c +++ b/refs/files-backend.c @@ -708,7 +708,7 @@ static enum ref_transaction_error lock_raw_ref(struct files_ref_store *refs, files_ref_path(refs, &ref_file, refname); retry: - switch (safe_create_leading_directories(ref_file.buf)) { + switch (safe_create_leading_directories(the_repository, ref_file.buf)) { case SCLD_OK: break; /* success */ case SCLD_EXISTS: @@ -1119,7 +1119,7 @@ retry_fn: strbuf_addstr(&path_copy, path); do { - scld_result = safe_create_leading_directories(path_copy.buf); + scld_result = safe_create_leading_directories(the_repository, path_copy.buf); if (scld_result == SCLD_OK) goto retry_fn; } while (scld_result == SCLD_VANISHED && create_directories_remaining-- > 0); diff --git a/remote.c b/remote.c index e7e10c7f4b..9fa3614e7a 100644 --- a/remote.c +++ b/remote.c @@ -12,7 +12,7 @@ #include "refs.h" #include "refspec.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "path.h" #include "commit.h" #include "diff.h" diff --git a/replace-object.c b/replace-object.c index 9a3cdd809a..7b8a09b5cb 100644 --- a/replace-object.c +++ b/replace-object.c @@ -2,7 +2,7 @@ #include "gettext.h" #include "hex.h" #include "oidmap.h" -#include "object-store-ll.h" +#include "object-store.h" #include "replace-object.h" #include "refs.h" #include "repository.h" diff --git a/replace-object.h b/replace-object.h index 66c41b938b..ba478eb30c 100644 --- a/replace-object.h +++ b/replace-object.h @@ -3,7 +3,7 @@ #include "oidmap.h" #include "repository.h" -#include "object-store-ll.h" +#include "object-store.h" struct replace_object { struct oidmap_entry original; diff --git a/repository.c b/repository.c index 6cbaf2e3da..9b3d6665fc 100644 --- a/repository.c +++ b/repository.c @@ -1,7 +1,7 @@ #include "git-compat-util.h" #include "abspath.h" #include "repository.h" -#include "object-store-ll.h" +#include "object-store.h" #include "config.h" #include "object.h" #include "lockfile.h" diff --git a/rerere.c b/rerere.c index 740e8ad1a0..3cd37c5f0a 100644 --- a/rerere.c +++ b/rerere.c @@ -18,7 +18,7 @@ #include "path.h" #include "pathspec.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "strmap.h" #define RESOLVED 0 @@ -860,7 +860,7 @@ static int do_plain_rerere(struct repository *r, string_list_insert(rr, path)->util = id; /* Ensure that the directory exists. */ - mkdir_in_gitdir(rerere_path(&buf, id, NULL)); + safe_create_dir_in_gitdir(the_repository, rerere_path(&buf, id, NULL)); } for (i = 0; i < rr->nr; i++) @@ -895,7 +895,8 @@ static int is_rerere_enabled(void) if (rerere_enabled < 0) return rr_cache_exists; - if (!rr_cache_exists && mkdir_in_gitdir(git_path_rr_cache())) + if (!rr_cache_exists && + safe_create_dir_in_gitdir(the_repository, git_path_rr_cache())) die(_("could not create directory '%s'"), git_path_rr_cache()); return 1; } diff --git a/revision.c b/revision.c index 550453ab70..2c36a9c179 100644 --- a/revision.c +++ b/revision.c @@ -8,7 +8,7 @@ #include "hex.h" #include "object-name.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "oidset.h" #include "tag.h" #include "blob.h" diff --git a/send-pack.c b/send-pack.c index 856a65d5f5..5005689cb5 100644 --- a/send-pack.c +++ b/send-pack.c @@ -4,7 +4,7 @@ #include "date.h" #include "gettext.h" #include "hex.h" -#include "object-store-ll.h" +#include "object-store.h" #include "pkt-line.h" #include "sideband.h" #include "run-command.h" diff --git a/sequencer.c b/sequencer.c index 9ea678364d..b5c4043757 100644 --- a/sequencer.c +++ b/sequencer.c @@ -13,7 +13,7 @@ #include "dir.h" #include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "object.h" #include "pager.h" #include "commit.h" @@ -4395,7 +4395,7 @@ static int write_update_refs_state(struct string_list *refs_to_oids) goto cleanup; } - if (safe_create_leading_directories(path)) { + if (safe_create_leading_directories(the_repository, path)) { result = error(_("unable to create leading directories of %s"), path); goto cleanup; @@ -4661,7 +4661,7 @@ static void create_autostash_internal(struct repository *r, strbuf_add_unique_abbrev(&buf, &oid, DEFAULT_ABBREV); if (path) { - if (safe_create_leading_directories_const(path)) + if (safe_create_leading_directories_const(the_repository, path)) die(_("Could not create directory for '%s'"), path); write_file(path, "%s", oid_to_hex(&oid)); diff --git a/server-info.c b/server-info.c index 1ca0e00d51..d6cd20a39d 100644 --- a/server-info.c +++ b/server-info.c @@ -11,7 +11,7 @@ #include "packfile.h" #include "path.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "server-info.h" #include "strbuf.h" #include "tempfile.h" @@ -88,7 +88,7 @@ static int update_info_file(struct repository *r, char *path, .old_sb = STRBUF_INIT }; - safe_create_leading_directories(path); + safe_create_leading_directories(r, path); f = mks_tempfile_m(tmp, 0666); if (!f) goto out; diff --git a/shallow.c b/shallow.c index 06c3266a3e..2f82ebd6e3 100644 --- a/shallow.c +++ b/shallow.c @@ -5,7 +5,7 @@ #include "repository.h" #include "tempfile.h" #include "lockfile.h" -#include "object-store-ll.h" +#include "object-store.h" #include "commit.h" #include "tag.h" #include "pkt-line.h" diff --git a/streaming.c b/streaming.c index 018b794d25..127d6b5d6a 100644 --- a/streaming.c +++ b/streaming.c @@ -10,7 +10,7 @@ #include "streaming.h" #include "repository.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "replace-object.h" #include "packfile.h" diff --git a/submodule-config.c b/submodule-config.c index d82b404b73..8630e27947 100644 --- a/submodule-config.c +++ b/submodule-config.c @@ -13,7 +13,7 @@ #include "submodule.h" #include "strbuf.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "parse-options.h" #include "thread-utils.h" #include "tree-walk.h" diff --git a/submodule.c b/submodule.c index 0821507eca..ead3fb5dad 100644 --- a/submodule.c +++ b/submodule.c @@ -27,7 +27,7 @@ #include "parse-options.h" #include "object-file.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "commit-reach.h" #include "read-cache-ll.h" #include "setup.h" @@ -2384,7 +2384,7 @@ static void relocate_single_git_dir_into_superproject(const char *path, if (validate_submodule_git_dir(new_gitdir.buf, sub->name) < 0) die(_("refusing to move '%s' into an existing git dir"), real_old_git_dir); - if (safe_create_leading_directories_const(new_gitdir.buf) < 0) + if (safe_create_leading_directories_const(the_repository, new_gitdir.buf) < 0) die(_("could not create directory '%s'"), new_gitdir.buf); real_new_git_dir = real_pathdup(new_gitdir.buf, 1); diff --git a/t/helper/test-pack-mtimes.c b/t/helper/test-pack-mtimes.c index f8f9afbb5b..50f5941bff 100644 --- a/t/helper/test-pack-mtimes.c +++ b/t/helper/test-pack-mtimes.c @@ -3,7 +3,7 @@ #include "test-tool.h" #include "hex.h" #include "strbuf.h" -#include "object-store-ll.h" +#include "object-store.h" #include "packfile.h" #include "pack-mtimes.h" #include "setup.h" diff --git a/t/helper/test-partial-clone.c b/t/helper/test-partial-clone.c index a1af9710c3..34f1aee558 100644 --- a/t/helper/test-partial-clone.c +++ b/t/helper/test-partial-clone.c @@ -1,7 +1,7 @@ #include "test-tool.h" #include "hex.h" #include "repository.h" -#include "object-store-ll.h" +#include "object-store.h" #include "setup.h" /* diff --git a/t/helper/test-read-graph.c b/t/helper/test-read-graph.c index 811dde1cb3..8b413b644b 100644 --- a/t/helper/test-read-graph.c +++ b/t/helper/test-read-graph.c @@ -3,7 +3,7 @@ #include "test-tool.h" #include "commit-graph.h" #include "repository.h" -#include "object-store-ll.h" +#include "object-store.h" #include "bloom.h" #include "setup.h" diff --git a/t/helper/test-read-midx.c b/t/helper/test-read-midx.c index fc63236961..ac81390899 100644 --- a/t/helper/test-read-midx.c +++ b/t/helper/test-read-midx.c @@ -4,7 +4,7 @@ #include "hex.h" #include "midx.h" #include "repository.h" -#include "object-store-ll.h" +#include "object-store.h" #include "pack-bitmap.h" #include "packfile.h" #include "setup.h" diff --git a/t/helper/test-ref-store.c b/t/helper/test-ref-store.c index 2ff67c067a..4cfc7c90b5 100644 --- a/t/helper/test-ref-store.c +++ b/t/helper/test-ref-store.c @@ -5,7 +5,7 @@ #include "refs.h" #include "setup.h" #include "worktree.h" -#include "object-store-ll.h" +#include "object-store.h" #include "path.h" #include "repository.h" #include "strbuf.h" diff --git a/tag.c b/tag.c index 8d9e9e2930..05be39067c 100644 --- a/tag.c +++ b/tag.c @@ -5,7 +5,7 @@ #include "environment.h" #include "tag.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "commit.h" #include "tree.h" #include "blob.h" diff --git a/tmp-objdir.c b/tmp-objdir.c index 31d16a4c2c..c38fbeb5e8 100644 --- a/tmp-objdir.c +++ b/tmp-objdir.c @@ -10,7 +10,7 @@ #include "strbuf.h" #include "strvec.h" #include "quote.h" -#include "object-store-ll.h" +#include "object-store.h" #include "repository.h" struct tmp_objdir { diff --git a/tree-walk.c b/tree-walk.c index a033397965..90655d5237 100644 --- a/tree-walk.c +++ b/tree-walk.c @@ -6,7 +6,7 @@ #include "gettext.h" #include "hex.h" #include "object-file.h" -#include "object-store-ll.h" +#include "object-store.h" #include "trace2.h" #include "tree.h" #include "pathspec.h" diff --git a/tree.c b/tree.c index ad86ad1ba9..b85f56267f 100644 --- a/tree.c +++ b/tree.c @@ -4,7 +4,7 @@ #include "hex.h" #include "tree.h" #include "object-name.h" -#include "object-store-ll.h" +#include "object-store.h" #include "commit.h" #include "alloc.h" #include "tree-walk.h" diff --git a/unpack-trees.c b/unpack-trees.c index cf5b73c84b..471837f032 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -26,7 +26,7 @@ #include "symlinks.h" #include "trace2.h" #include "fsmonitor.h" -#include "object-store-ll.h" +#include "object-store.h" #include "promisor-remote.h" #include "entry.h" #include "parallel-checkout.h" diff --git a/upload-pack.c b/upload-pack.c index 02ce633602..30e4630f3a 100644 --- a/upload-pack.c +++ b/upload-pack.c @@ -10,7 +10,7 @@ #include "pkt-line.h" #include "sideband.h" #include "repository.h" -#include "object-store-ll.h" +#include "object-store.h" #include "oid-array.h" #include "object.h" #include "commit.h" diff --git a/walker.c b/walker.c index 1cf3da0219..4fedc19f34 100644 --- a/walker.c +++ b/walker.c @@ -5,7 +5,7 @@ #include "hex.h" #include "walker.h" #include "repository.h" -#include "object-store-ll.h" +#include "object-store.h" #include "commit.h" #include "strbuf.h" #include "tree.h" diff --git a/wrapper.c b/wrapper.c index 8b98593149..3c79778055 100644 --- a/wrapper.c +++ b/wrapper.c @@ -829,3 +829,51 @@ uint32_t git_rand(unsigned flags) return result; } + +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; +} diff --git a/xdiff-interface.c b/xdiff-interface.c index 77712811ff..1edcd319e6 100644 --- a/xdiff-interface.c +++ b/xdiff-interface.c @@ -5,7 +5,7 @@ #include "gettext.h" #include "config.h" #include "hex.h" -#include "object-store-ll.h" +#include "object-store.h" #include "strbuf.h" #include "xdiff-interface.h" #include "xdiff/xtypes.h"