diff options
| author | Junio C Hamano <gitster@pobox.com> | 2025-04-24 11:37:21 -0700 |
|---|---|---|
| committer | Junio C Hamano <gitster@pobox.com> | 2025-04-24 11:37:21 -0700 |
| commit | d61ff9c237b05f9cff0831d4bde546ed4a9c3c42 (patch) | |
| tree | 4a787bfa36ba05fbcaefec1334b520a9f175935b | |
| parent | 4bbb303af69990ccd05fe3a2eb58a1ce036f8220 (diff) | |
| parent | 68cd492a3e662c75dec364986c81e94716d4ac56 (diff) | |
| download | git-d61ff9c237b05f9cff0831d4bde546ed4a9c3c42.tar.gz | |
Merge branch 'ps/object-file-cleanup' into ps/object-store-cleanup
* ps/object-file-cleanup:
object-store: merge "object-store-ll.h" and "object-store.h"
object-store: remove global array of cached objects
object: split out functions relating to object store subsystem
object-file: drop `index_blob_stream()`
object-file: split up concerns of `HASH_*` flags
object-file: split out functions relating to object store subsystem
object-file: move `xmmap()` into "wrapper.c"
object-file: move `git_open_cloexec()` to "compat/open.c"
object-file: move `safe_create_leading_directories()` into "path.c"
object-file: move `mkdir_in_gitdir()` into "path.c"
150 files changed, 6223 insertions, 2064 deletions
@@ -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 @@ -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" @@ -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" @@ -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" @@ -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" @@ -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, "</array>\n</dict>\n</plist>\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 55a7d471dc..99fe7a0c56 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" @@ -555,7 +556,7 @@ 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; @@ -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" @@ -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; +} @@ -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" @@ -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" @@ -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" @@ -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); @@ -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" @@ -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)) @@ -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; @@ -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" @@ -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/merge-recursive.c b/merge-recursive.c new file mode 100644 index 0000000000..b852f46767 --- /dev/null +++ b/merge-recursive.c @@ -0,0 +1,4079 @@ +/* + * Recursive Merge algorithm stolen from git-merge-recursive.py by + * Fredrik Kuivinen. + * The thieves were Alex Riesen and Johannes Schindelin, in June/July 2006 + */ + +#define USE_THE_REPOSITORY_VARIABLE +#define DISABLE_SIGN_COMPARE_WARNINGS + +#include "git-compat-util.h" +#include "merge-recursive.h" + +#include "alloc.h" +#include "cache-tree.h" +#include "commit.h" +#include "commit-reach.h" +#include "config.h" +#include "diff.h" +#include "diffcore.h" +#include "dir.h" +#include "environment.h" +#include "gettext.h" +#include "hex.h" +#include "merge-ll.h" +#include "lockfile.h" +#include "match-trees.h" +#include "name-hash.h" +#include "object-file.h" +#include "object-name.h" +#include "object-store.h" +#include "path.h" +#include "repository.h" +#include "revision.h" +#include "sparse-index.h" +#include "string-list.h" +#include "symlinks.h" +#include "tag.h" +#include "tree-walk.h" +#include "unpack-trees.h" +#include "xdiff-interface.h" + +struct merge_options_internal { + int call_depth; + int needed_rename_limit; + struct hashmap current_file_dir_set; + struct string_list df_conflict_file_set; + struct unpack_trees_options unpack_opts; + struct index_state orig_index; +}; + +struct path_hashmap_entry { + struct hashmap_entry e; + char path[FLEX_ARRAY]; +}; + +static int path_hashmap_cmp(const void *cmp_data UNUSED, + const struct hashmap_entry *eptr, + const struct hashmap_entry *entry_or_key, + const void *keydata) +{ + const struct path_hashmap_entry *a, *b; + const char *key = keydata; + + a = container_of(eptr, const struct path_hashmap_entry, e); + b = container_of(entry_or_key, const struct path_hashmap_entry, e); + + return fspathcmp(a->path, key ? key : b->path); +} + +/* + * For dir_rename_entry, directory names are stored as a full path from the + * toplevel of the repository and do not include a trailing '/'. Also: + * + * dir: original name of directory being renamed + * non_unique_new_dir: if true, could not determine new_dir + * new_dir: final name of directory being renamed + * possible_new_dirs: temporary used to help determine new_dir; see comments + * in get_directory_renames() for details + */ +struct dir_rename_entry { + struct hashmap_entry ent; + char *dir; + unsigned non_unique_new_dir:1; + struct strbuf new_dir; + struct string_list possible_new_dirs; +}; + +static struct dir_rename_entry *dir_rename_find_entry(struct hashmap *hashmap, + char *dir) +{ + struct dir_rename_entry key; + + if (!dir) + return NULL; + hashmap_entry_init(&key.ent, strhash(dir)); + key.dir = dir; + return hashmap_get_entry(hashmap, &key, ent, NULL); +} + +static int dir_rename_cmp(const void *cmp_data UNUSED, + const struct hashmap_entry *eptr, + const struct hashmap_entry *entry_or_key, + const void *keydata UNUSED) +{ + const struct dir_rename_entry *e1, *e2; + + e1 = container_of(eptr, const struct dir_rename_entry, ent); + e2 = container_of(entry_or_key, const struct dir_rename_entry, ent); + + return strcmp(e1->dir, e2->dir); +} + +static void dir_rename_init(struct hashmap *map) +{ + hashmap_init(map, dir_rename_cmp, NULL, 0); +} + +static void dir_rename_entry_init(struct dir_rename_entry *entry, + char *directory) +{ + hashmap_entry_init(&entry->ent, strhash(directory)); + entry->dir = directory; + entry->non_unique_new_dir = 0; + strbuf_init(&entry->new_dir, 0); + string_list_init_nodup(&entry->possible_new_dirs); +} + +struct collision_entry { + struct hashmap_entry ent; + char *target_file; + struct string_list source_files; + unsigned reported_already:1; +}; + +static struct collision_entry *collision_find_entry(struct hashmap *hashmap, + char *target_file) +{ + struct collision_entry key; + + hashmap_entry_init(&key.ent, strhash(target_file)); + key.target_file = target_file; + return hashmap_get_entry(hashmap, &key, ent, NULL); +} + +static int collision_cmp(const void *cmp_data UNUSED, + const struct hashmap_entry *eptr, + const struct hashmap_entry *entry_or_key, + const void *keydata UNUSED) +{ + const struct collision_entry *e1, *e2; + + e1 = container_of(eptr, const struct collision_entry, ent); + e2 = container_of(entry_or_key, const struct collision_entry, ent); + + return strcmp(e1->target_file, e2->target_file); +} + +static void collision_init(struct hashmap *map) +{ + hashmap_init(map, collision_cmp, NULL, 0); +} + +static void flush_output(struct merge_options *opt) +{ + if (opt->buffer_output < 2 && opt->obuf.len) { + fputs(opt->obuf.buf, stdout); + strbuf_reset(&opt->obuf); + } +} + +__attribute__((format (printf, 2, 3))) +static int err(struct merge_options *opt, const char *err, ...) +{ + va_list params; + + if (opt->buffer_output < 2) + flush_output(opt); + else { + strbuf_complete(&opt->obuf, '\n'); + strbuf_addstr(&opt->obuf, "error: "); + } + va_start(params, err); + strbuf_vaddf(&opt->obuf, err, params); + va_end(params); + if (opt->buffer_output > 1) + strbuf_addch(&opt->obuf, '\n'); + else { + error("%s", opt->obuf.buf); + strbuf_reset(&opt->obuf); + } + + return -1; +} + +static struct tree *shift_tree_object(struct repository *repo, + struct tree *one, struct tree *two, + const char *subtree_shift) +{ + struct object_id shifted; + + if (!*subtree_shift) { + shift_tree(repo, &one->object.oid, &two->object.oid, &shifted, 0); + } else { + shift_tree_by(repo, &one->object.oid, &two->object.oid, &shifted, + subtree_shift); + } + if (oideq(&two->object.oid, &shifted)) + return two; + return lookup_tree(repo, &shifted); +} + +static inline void set_commit_tree(struct commit *c, struct tree *t) +{ + c->maybe_tree = t; +} + +static struct commit *make_virtual_commit(struct repository *repo, + struct tree *tree, + const char *comment) +{ + struct commit *commit = alloc_commit_node(repo); + + set_merge_remote_desc(commit, comment, (struct object *)commit); + set_commit_tree(commit, tree); + commit->object.parsed = 1; + return commit; +} + +enum rename_type { + RENAME_NORMAL = 0, + RENAME_VIA_DIR, + RENAME_ADD, + RENAME_DELETE, + RENAME_ONE_FILE_TO_ONE, + RENAME_ONE_FILE_TO_TWO, + RENAME_TWO_FILES_TO_ONE +}; + +/* + * Since we want to write the index eventually, we cannot reuse the index + * for these (temporary) data. + */ +struct stage_data { + struct diff_filespec stages[4]; /* mostly for oid & mode; maybe path */ + struct rename_conflict_info *rename_conflict_info; + unsigned processed:1, + rename_conflict_info_owned:1; +}; + +struct rename { + unsigned processed:1; + struct diff_filepair *pair; + const char *branch; /* branch that the rename occurred on */ + /* + * If directory rename detection affected this rename, what was its + * original type ('A' or 'R') and it's original destination before + * the directory rename (otherwise, '\0' and NULL for these two vars). + */ + char dir_rename_original_type; + char *dir_rename_original_dest; + /* + * Purpose of src_entry and dst_entry: + * + * If 'before' is renamed to 'after' then src_entry will contain + * the versions of 'before' from the merge_base, HEAD, and MERGE in + * stages 1, 2, and 3; dst_entry will contain the respective + * versions of 'after' in corresponding locations. Thus, we have a + * total of six modes and oids, though some will be null. (Stage 0 + * is ignored; we're interested in handling conflicts.) + * + * Since we don't turn on break-rewrites by default, neither + * src_entry nor dst_entry can have all three of their stages have + * non-null oids, meaning at most four of the six will be non-null. + * Also, since this is a rename, both src_entry and dst_entry will + * have at least one non-null oid, meaning at least two will be + * non-null. Of the six oids, a typical rename will have three be + * non-null. Only two implies a rename/delete, and four implies a + * rename/add. + */ + struct stage_data *src_entry; + struct stage_data *dst_entry; +}; + +struct rename_conflict_info { + enum rename_type rename_type; + struct rename *ren1; + struct rename *ren2; +}; + +static inline void setup_rename_conflict_info(enum rename_type rename_type, + struct merge_options *opt, + struct rename *ren1, + struct rename *ren2) +{ + struct rename_conflict_info *ci; + + /* + * When we have two renames involved, it's easiest to get the + * correct things into stage 2 and 3, and to make sure that the + * content merge puts HEAD before the other branch if we just + * ensure that branch1 == opt->branch1. So, simply flip arguments + * around if we don't have that. + */ + if (ren2 && ren1->branch != opt->branch1) { + setup_rename_conflict_info(rename_type, opt, ren2, ren1); + return; + } + + CALLOC_ARRAY(ci, 1); + ci->rename_type = rename_type; + ci->ren1 = ren1; + ci->ren2 = ren2; + + ci->ren1->dst_entry->processed = 0; + ci->ren1->dst_entry->rename_conflict_info = ci; + ci->ren1->dst_entry->rename_conflict_info_owned = 1; + if (ren2) { + ci->ren2->dst_entry->rename_conflict_info = ci; + } +} + +static int show(struct merge_options *opt, int v) +{ + return (!opt->priv->call_depth && opt->verbosity >= v) || + opt->verbosity >= 5; +} + +__attribute__((format (printf, 3, 4))) +static void output(struct merge_options *opt, int v, const char *fmt, ...) +{ + va_list ap; + + if (!show(opt, v)) + return; + + strbuf_addchars(&opt->obuf, ' ', opt->priv->call_depth * 2); + + va_start(ap, fmt); + strbuf_vaddf(&opt->obuf, fmt, ap); + va_end(ap); + + strbuf_addch(&opt->obuf, '\n'); + if (!opt->buffer_output) + flush_output(opt); +} + +static void repo_output_commit_title(struct merge_options *opt, + struct repository *repo, + struct commit *commit) +{ + struct merge_remote_desc *desc; + + strbuf_addchars(&opt->obuf, ' ', opt->priv->call_depth * 2); + desc = merge_remote_util(commit); + if (desc) + strbuf_addf(&opt->obuf, "virtual %s\n", desc->name); + else { + strbuf_repo_add_unique_abbrev(&opt->obuf, repo, + &commit->object.oid, + DEFAULT_ABBREV); + strbuf_addch(&opt->obuf, ' '); + if (repo_parse_commit(repo, commit) != 0) + strbuf_addstr(&opt->obuf, _("(bad commit)\n")); + else { + const char *title; + const char *msg = repo_get_commit_buffer(repo, commit, NULL); + int len = find_commit_subject(msg, &title); + if (len) + strbuf_addf(&opt->obuf, "%.*s\n", len, title); + repo_unuse_commit_buffer(repo, commit, msg); + } + } + flush_output(opt); +} + +static void output_commit_title(struct merge_options *opt, struct commit *commit) +{ + repo_output_commit_title(opt, the_repository, commit); +} + +static int add_cacheinfo(struct merge_options *opt, + const struct diff_filespec *blob, + const char *path, int stage, int refresh, int options) +{ + struct index_state *istate = opt->repo->index; + struct cache_entry *ce; + int ret; + + ce = make_cache_entry(istate, blob->mode, &blob->oid, path, stage, 0); + if (!ce) + return err(opt, _("add_cacheinfo failed for path '%s'; merge aborting."), path); + + ret = add_index_entry(istate, ce, options); + if (refresh) { + struct cache_entry *nce; + + nce = refresh_cache_entry(istate, ce, + CE_MATCH_REFRESH | CE_MATCH_IGNORE_MISSING); + if (!nce) + return err(opt, _("add_cacheinfo failed to refresh for path '%s'; merge aborting."), path); + if (nce != ce) + ret = add_index_entry(istate, nce, options); + } + return ret; +} + +static inline int merge_detect_rename(struct merge_options *opt) +{ + return (opt->detect_renames >= 0) ? opt->detect_renames : 1; +} + +static void init_tree_desc_from_tree(struct tree_desc *desc, struct tree *tree) +{ + if (parse_tree(tree) < 0) + exit(128); + init_tree_desc(desc, &tree->object.oid, tree->buffer, tree->size); +} + +static int unpack_trees_start(struct merge_options *opt, + struct tree *common, + struct tree *head, + struct tree *merge) +{ + int rc; + struct tree_desc t[3]; + struct index_state tmp_index = INDEX_STATE_INIT(opt->repo); + + memset(&opt->priv->unpack_opts, 0, sizeof(opt->priv->unpack_opts)); + if (opt->priv->call_depth) + opt->priv->unpack_opts.index_only = 1; + else { + opt->priv->unpack_opts.update = 1; + /* FIXME: should only do this if !overwrite_ignore */ + opt->priv->unpack_opts.preserve_ignored = 0; + } + opt->priv->unpack_opts.merge = 1; + opt->priv->unpack_opts.head_idx = 2; + opt->priv->unpack_opts.fn = threeway_merge; + opt->priv->unpack_opts.src_index = opt->repo->index; + opt->priv->unpack_opts.dst_index = &tmp_index; + opt->priv->unpack_opts.aggressive = !merge_detect_rename(opt); + setup_unpack_trees_porcelain(&opt->priv->unpack_opts, "merge"); + + init_tree_desc_from_tree(t+0, common); + init_tree_desc_from_tree(t+1, head); + init_tree_desc_from_tree(t+2, merge); + + rc = unpack_trees(3, t, &opt->priv->unpack_opts); + cache_tree_free(&opt->repo->index->cache_tree); + + /* + * Update opt->repo->index to match the new results, AFTER saving a + * copy in opt->priv->orig_index. Update src_index to point to the + * saved copy. (verify_uptodate() checks src_index, and the original + * index is the one that had the necessary modification timestamps.) + */ + opt->priv->orig_index = *opt->repo->index; + *opt->repo->index = tmp_index; + opt->priv->unpack_opts.src_index = &opt->priv->orig_index; + + return rc; +} + +static void unpack_trees_finish(struct merge_options *opt) +{ + discard_index(&opt->priv->orig_index); + clear_unpack_trees_porcelain(&opt->priv->unpack_opts); +} + +static int save_files_dirs(const struct object_id *oid UNUSED, + struct strbuf *base, const char *path, + unsigned int mode, void *context) +{ + struct path_hashmap_entry *entry; + int baselen = base->len; + struct merge_options *opt = context; + + strbuf_addstr(base, path); + + FLEX_ALLOC_MEM(entry, path, base->buf, base->len); + hashmap_entry_init(&entry->e, fspathhash(entry->path)); + hashmap_add(&opt->priv->current_file_dir_set, &entry->e); + + strbuf_setlen(base, baselen); + return (S_ISDIR(mode) ? READ_TREE_RECURSIVE : 0); +} + +static void get_files_dirs(struct merge_options *opt, struct tree *tree) +{ + struct pathspec match_all; + memset(&match_all, 0, sizeof(match_all)); + read_tree(opt->repo, tree, + &match_all, save_files_dirs, opt); +} + +static int get_tree_entry_if_blob(struct repository *r, + const struct object_id *tree, + const char *path, + struct diff_filespec *dfs) +{ + int ret; + + ret = get_tree_entry(r, tree, path, &dfs->oid, &dfs->mode); + if (S_ISDIR(dfs->mode)) { + oidcpy(&dfs->oid, null_oid(the_hash_algo)); + dfs->mode = 0; + } + return ret; +} + +/* + * Returns an index_entry instance which doesn't have to correspond to + * a real cache entry in Git's index. + */ +static struct stage_data *insert_stage_data(struct repository *r, + const char *path, + struct tree *o, struct tree *a, struct tree *b, + struct string_list *entries) +{ + struct string_list_item *item; + struct stage_data *e = xcalloc(1, sizeof(struct stage_data)); + get_tree_entry_if_blob(r, &o->object.oid, path, &e->stages[1]); + get_tree_entry_if_blob(r, &a->object.oid, path, &e->stages[2]); + get_tree_entry_if_blob(r, &b->object.oid, path, &e->stages[3]); + item = string_list_insert(entries, path); + item->util = e; + return e; +} + +/* + * Create a dictionary mapping file names to stage_data objects. The + * dictionary contains one entry for every path with a non-zero stage entry. + */ +static struct string_list *get_unmerged(struct index_state *istate) +{ + struct string_list *unmerged = xmalloc(sizeof(struct string_list)); + int i; + + string_list_init_dup(unmerged); + + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(istate); + for (i = 0; i < istate->cache_nr; i++) { + struct string_list_item *item; + struct stage_data *e; + const struct cache_entry *ce = istate->cache[i]; + if (!ce_stage(ce)) + continue; + + item = string_list_lookup(unmerged, ce->name); + if (!item) { + item = string_list_insert(unmerged, ce->name); + item->util = xcalloc(1, sizeof(struct stage_data)); + } + e = item->util; + e->stages[ce_stage(ce)].mode = ce->ce_mode; + oidcpy(&e->stages[ce_stage(ce)].oid, &ce->oid); + } + + return unmerged; +} + +static int string_list_df_name_compare(const char *one, const char *two) +{ + int onelen = strlen(one); + int twolen = strlen(two); + /* + * Here we only care that entries for D/F conflicts are + * adjacent, in particular with the file of the D/F conflict + * appearing before files below the corresponding directory. + * The order of the rest of the list is irrelevant for us. + * + * To achieve this, we sort with df_name_compare and provide + * the mode S_IFDIR so that D/F conflicts will sort correctly. + * We use the mode S_IFDIR for everything else for simplicity, + * since in other cases any changes in their order due to + * sorting cause no problems for us. + */ + int cmp = df_name_compare(one, onelen, S_IFDIR, + two, twolen, S_IFDIR); + /* + * Now that 'foo' and 'foo/bar' compare equal, we have to make sure + * that 'foo' comes before 'foo/bar'. + */ + if (cmp) + return cmp; + return onelen - twolen; +} + +static void record_df_conflict_files(struct merge_options *opt, + struct string_list *entries) +{ + /* If there is a D/F conflict and the file for such a conflict + * currently exists in the working tree, we want to allow it to be + * removed to make room for the corresponding directory if needed. + * The files underneath the directories of such D/F conflicts will + * be processed before the corresponding file involved in the D/F + * conflict. If the D/F directory ends up being removed by the + * merge, then we won't have to touch the D/F file. If the D/F + * directory needs to be written to the working copy, then the D/F + * file will simply be removed (in make_room_for_path()) to make + * room for the necessary paths. Note that if both the directory + * and the file need to be present, then the D/F file will be + * reinstated with a new unique name at the time it is processed. + */ + struct string_list df_sorted_entries = STRING_LIST_INIT_NODUP; + const char *last_file = NULL; + int last_len = 0; + int i; + + /* + * If we're merging merge-bases, we don't want to bother with + * any working directory changes. + */ + if (opt->priv->call_depth) + return; + + /* Ensure D/F conflicts are adjacent in the entries list. */ + for (i = 0; i < entries->nr; i++) { + struct string_list_item *next = &entries->items[i]; + string_list_append(&df_sorted_entries, next->string)->util = + next->util; + } + df_sorted_entries.cmp = string_list_df_name_compare; + string_list_sort(&df_sorted_entries); + + string_list_clear(&opt->priv->df_conflict_file_set, 1); + for (i = 0; i < df_sorted_entries.nr; i++) { + const char *path = df_sorted_entries.items[i].string; + int len = strlen(path); + struct stage_data *e = df_sorted_entries.items[i].util; + + /* + * Check if last_file & path correspond to a D/F conflict; + * i.e. whether path is last_file+'/'+<something>. + * If so, record that it's okay to remove last_file to make + * room for path and friends if needed. + */ + if (last_file && + len > last_len && + memcmp(path, last_file, last_len) == 0 && + path[last_len] == '/') { + string_list_insert(&opt->priv->df_conflict_file_set, last_file); + } + + /* + * Determine whether path could exist as a file in the + * working directory as a possible D/F conflict. This + * will only occur when it exists in stage 2 as a + * file. + */ + if (S_ISREG(e->stages[2].mode) || S_ISLNK(e->stages[2].mode)) { + last_file = path; + last_len = len; + } else { + last_file = NULL; + } + } + string_list_clear(&df_sorted_entries, 0); +} + +static int update_stages(struct merge_options *opt, const char *path, + const struct diff_filespec *o, + const struct diff_filespec *a, + const struct diff_filespec *b) +{ + + /* + * NOTE: It is usually a bad idea to call update_stages on a path + * before calling update_file on that same path, since it can + * sometimes lead to spurious "refusing to lose untracked file..." + * messages from update_file (via make_room_for path via + * would_lose_untracked). Instead, reverse the order of the calls + * (executing update_file first and then update_stages). + */ + int clear = 1; + int options = ADD_CACHE_OK_TO_ADD | ADD_CACHE_SKIP_DFCHECK; + if (clear) + if (remove_file_from_index(opt->repo->index, path)) + return -1; + if (o) + if (add_cacheinfo(opt, o, path, 1, 0, options)) + return -1; + if (a) + if (add_cacheinfo(opt, a, path, 2, 0, options)) + return -1; + if (b) + if (add_cacheinfo(opt, b, path, 3, 0, options)) + return -1; + return 0; +} + +static void update_entry(struct stage_data *entry, + struct diff_filespec *o, + struct diff_filespec *a, + struct diff_filespec *b) +{ + entry->processed = 0; + entry->stages[1].mode = o->mode; + entry->stages[2].mode = a->mode; + entry->stages[3].mode = b->mode; + oidcpy(&entry->stages[1].oid, &o->oid); + oidcpy(&entry->stages[2].oid, &a->oid); + oidcpy(&entry->stages[3].oid, &b->oid); +} + +static int remove_file(struct merge_options *opt, int clean, + const char *path, int no_wd) +{ + int update_cache = opt->priv->call_depth || clean; + int update_working_directory = !opt->priv->call_depth && !no_wd; + + if (update_cache) { + if (remove_file_from_index(opt->repo->index, path)) + return -1; + } + if (update_working_directory) { + if (ignore_case) { + struct cache_entry *ce; + ce = index_file_exists(opt->repo->index, path, strlen(path), + ignore_case); + if (ce && ce_stage(ce) == 0 && strcmp(path, ce->name)) + return 0; + } + if (remove_path(path)) + return -1; + } + return 0; +} + +/* add a string to a strbuf, but converting "/" to "_" */ +static void add_flattened_path(struct strbuf *out, const char *s) +{ + size_t i = out->len; + strbuf_addstr(out, s); + for (; i < out->len; i++) + if (out->buf[i] == '/') + out->buf[i] = '_'; +} + +static char *unique_path(struct merge_options *opt, + const char *path, + const char *branch) +{ + struct path_hashmap_entry *entry; + struct strbuf newpath = STRBUF_INIT; + int suffix = 0; + size_t base_len; + + strbuf_addf(&newpath, "%s~", path); + add_flattened_path(&newpath, branch); + + base_len = newpath.len; + while (hashmap_get_from_hash(&opt->priv->current_file_dir_set, + fspathhash(newpath.buf), newpath.buf) || + (!opt->priv->call_depth && file_exists(newpath.buf))) { + strbuf_setlen(&newpath, base_len); + strbuf_addf(&newpath, "_%d", suffix++); + } + + FLEX_ALLOC_MEM(entry, path, newpath.buf, newpath.len); + hashmap_entry_init(&entry->e, fspathhash(entry->path)); + hashmap_add(&opt->priv->current_file_dir_set, &entry->e); + return strbuf_detach(&newpath, NULL); +} + +/** + * Check whether a directory in the index is in the way of an incoming + * file. Return 1 if so. If check_working_copy is non-zero, also + * check the working directory. If empty_ok is non-zero, also return + * 0 in the case where the working-tree dir exists but is empty. + */ +static int dir_in_way(struct index_state *istate, const char *path, + int check_working_copy, int empty_ok) +{ + int pos; + struct strbuf dirpath = STRBUF_INIT; + struct stat st; + + strbuf_addstr(&dirpath, path); + strbuf_addch(&dirpath, '/'); + + pos = index_name_pos(istate, dirpath.buf, dirpath.len); + + if (pos < 0) + pos = -1 - pos; + if (pos < istate->cache_nr && + !strncmp(dirpath.buf, istate->cache[pos]->name, dirpath.len)) { + strbuf_release(&dirpath); + return 1; + } + + strbuf_release(&dirpath); + return check_working_copy && !lstat(path, &st) && S_ISDIR(st.st_mode) && + !(empty_ok && is_empty_dir(path)) && + !has_symlink_leading_path(path, strlen(path)); +} + +/* + * Returns whether path was tracked in the index before the merge started, + * and its oid and mode match the specified values + */ +static int was_tracked_and_matches(struct merge_options *opt, const char *path, + const struct diff_filespec *blob) +{ + int pos = index_name_pos(&opt->priv->orig_index, path, strlen(path)); + struct cache_entry *ce; + + if (0 > pos) + /* we were not tracking this path before the merge */ + return 0; + + /* See if the file we were tracking before matches */ + ce = opt->priv->orig_index.cache[pos]; + return (oideq(&ce->oid, &blob->oid) && ce->ce_mode == blob->mode); +} + +/* + * Returns whether path was tracked in the index before the merge started + */ +static int was_tracked(struct merge_options *opt, const char *path) +{ + int pos = index_name_pos(&opt->priv->orig_index, path, strlen(path)); + + if (0 <= pos) + /* we were tracking this path before the merge */ + return 1; + + return 0; +} + +static int would_lose_untracked(struct merge_options *opt, const char *path) +{ + struct index_state *istate = opt->repo->index; + + /* + * This may look like it can be simplified to: + * return !was_tracked(opt, path) && file_exists(path) + * but it can't. This function needs to know whether path was in + * the working tree due to EITHER having been tracked in the index + * before the merge OR having been put into the working copy and + * index by unpack_trees(). Due to that either-or requirement, we + * check the current index instead of the original one. + * + * Note that we do not need to worry about merge-recursive itself + * updating the index after unpack_trees() and before calling this + * function, because we strictly require all code paths in + * merge-recursive to update the working tree first and the index + * second. Doing otherwise would break + * update_file()/would_lose_untracked(); see every comment in this + * file which mentions "update_stages". + */ + int pos = index_name_pos(istate, path, strlen(path)); + + if (pos < 0) + pos = -1 - pos; + while (pos < istate->cache_nr && + !strcmp(path, istate->cache[pos]->name)) { + /* + * If stage #0, it is definitely tracked. + * If it has stage #2 then it was tracked + * before this merge started. All other + * cases the path was not tracked. + */ + switch (ce_stage(istate->cache[pos])) { + case 0: + case 2: + return 0; + } + pos++; + } + return file_exists(path); +} + +static int was_dirty(struct merge_options *opt, const char *path) +{ + struct cache_entry *ce; + int dirty = 1; + + if (opt->priv->call_depth || !was_tracked(opt, path)) + return !dirty; + + ce = index_file_exists(opt->priv->unpack_opts.src_index, + path, strlen(path), ignore_case); + dirty = verify_uptodate(ce, &opt->priv->unpack_opts) != 0; + return dirty; +} + +static int make_room_for_path(struct merge_options *opt, const char *path) +{ + int status, i; + const char *msg = _("failed to create path '%s'%s"); + + /* Unlink any D/F conflict files that are in the way */ + for (i = 0; i < opt->priv->df_conflict_file_set.nr; i++) { + const char *df_path = opt->priv->df_conflict_file_set.items[i].string; + size_t pathlen = strlen(path); + size_t df_pathlen = strlen(df_path); + if (df_pathlen < pathlen && + path[df_pathlen] == '/' && + strncmp(path, df_path, df_pathlen) == 0) { + output(opt, 3, + _("Removing %s to make room for subdirectory\n"), + df_path); + unlink(df_path); + unsorted_string_list_delete_item(&opt->priv->df_conflict_file_set, + i, 0); + break; + } + } + + /* Make sure leading directories are created */ + status = safe_create_leading_directories_const(the_repository, path); + if (status) { + if (status == SCLD_EXISTS) + /* something else exists */ + return err(opt, msg, path, _(": perhaps a D/F conflict?")); + return err(opt, msg, path, ""); + } + + /* + * Do not unlink a file in the work tree if we are not + * tracking it. + */ + if (would_lose_untracked(opt, path)) + return err(opt, _("refusing to lose untracked file at '%s'"), + path); + + /* Successful unlink is good.. */ + if (!unlink(path)) + return 0; + /* .. and so is no existing file */ + if (errno == ENOENT) + return 0; + /* .. but not some other error (who really cares what?) */ + return err(opt, msg, path, _(": perhaps a D/F conflict?")); +} + +static int update_file_flags(struct merge_options *opt, + const struct diff_filespec *contents, + const char *path, + int update_cache, + int update_wd) +{ + int ret = 0; + + if (opt->priv->call_depth) + update_wd = 0; + + if (update_wd) { + enum object_type type; + void *buf; + unsigned long size; + + if (S_ISGITLINK(contents->mode)) { + /* + * We may later decide to recursively descend into + * the submodule directory and update its index + * and/or work tree, but we do not do that now. + */ + update_wd = 0; + goto update_index; + } + + buf = repo_read_object_file(the_repository, &contents->oid, + &type, &size); + if (!buf) { + ret = err(opt, _("cannot read object %s '%s'"), + oid_to_hex(&contents->oid), path); + goto free_buf; + } + if (type != OBJ_BLOB) { + ret = err(opt, _("blob expected for %s '%s'"), + oid_to_hex(&contents->oid), path); + goto free_buf; + } + if (S_ISREG(contents->mode)) { + struct strbuf strbuf = STRBUF_INIT; + if (convert_to_working_tree(opt->repo->index, + path, buf, size, &strbuf, NULL)) { + free(buf); + size = strbuf.len; + buf = strbuf_detach(&strbuf, NULL); + } + } + + if (make_room_for_path(opt, path) < 0) { + update_wd = 0; + goto free_buf; + } + if (S_ISREG(contents->mode) || + (!has_symlinks && S_ISLNK(contents->mode))) { + int fd; + int mode = (contents->mode & 0100 ? 0777 : 0666); + + fd = open(path, O_WRONLY | O_TRUNC | O_CREAT, mode); + if (fd < 0) { + ret = err(opt, _("failed to open '%s': %s"), + path, strerror(errno)); + goto free_buf; + } + write_in_full(fd, buf, size); + close(fd); + } else if (S_ISLNK(contents->mode)) { + char *lnk = xmemdupz(buf, size); + safe_create_leading_directories_const(the_repository, path); + unlink(path); + if (symlink(lnk, path)) + ret = err(opt, _("failed to symlink '%s': %s"), + path, strerror(errno)); + free(lnk); + } else + ret = err(opt, + _("do not know what to do with %06o %s '%s'"), + contents->mode, oid_to_hex(&contents->oid), path); + free_buf: + free(buf); + } +update_index: + if (!ret && update_cache) { + int refresh = (!opt->priv->call_depth && + contents->mode != S_IFGITLINK); + if (add_cacheinfo(opt, contents, path, 0, refresh, + ADD_CACHE_OK_TO_ADD)) + return -1; + } + return ret; +} + +static int update_file(struct merge_options *opt, + int clean, + const struct diff_filespec *contents, + const char *path) +{ + return update_file_flags(opt, contents, path, + opt->priv->call_depth || clean, !opt->priv->call_depth); +} + +/* Low level file merging, update and removal */ + +struct merge_file_info { + struct diff_filespec blob; /* mostly use oid & mode; sometimes path */ + unsigned clean:1, + merge:1; +}; + +static int merge_3way(struct merge_options *opt, + mmbuffer_t *result_buf, + const struct diff_filespec *o, + const struct diff_filespec *a, + const struct diff_filespec *b, + const char *branch1, + const char *branch2, + const int extra_marker_size) +{ + mmfile_t orig, src1, src2; + struct ll_merge_options ll_opts = LL_MERGE_OPTIONS_INIT; + char *base, *name1, *name2; + enum ll_merge_result merge_status; + + ll_opts.renormalize = opt->renormalize; + ll_opts.extra_marker_size = extra_marker_size; + ll_opts.xdl_opts = opt->xdl_opts; + ll_opts.conflict_style = opt->conflict_style; + + if (opt->priv->call_depth) { + ll_opts.virtual_ancestor = 1; + ll_opts.variant = 0; + } else { + switch (opt->recursive_variant) { + case MERGE_VARIANT_OURS: + ll_opts.variant = XDL_MERGE_FAVOR_OURS; + break; + case MERGE_VARIANT_THEIRS: + ll_opts.variant = XDL_MERGE_FAVOR_THEIRS; + break; + default: + ll_opts.variant = 0; + break; + } + } + + assert(a->path && b->path && o->path && opt->ancestor); + if (strcmp(a->path, b->path) || strcmp(a->path, o->path) != 0) { + base = mkpathdup("%s:%s", opt->ancestor, o->path); + name1 = mkpathdup("%s:%s", branch1, a->path); + name2 = mkpathdup("%s:%s", branch2, b->path); + } else { + base = mkpathdup("%s", opt->ancestor); + name1 = mkpathdup("%s", branch1); + name2 = mkpathdup("%s", branch2); + } + + read_mmblob(&orig, &o->oid); + read_mmblob(&src1, &a->oid); + read_mmblob(&src2, &b->oid); + + /* + * FIXME: Using a->path for normalization rules in ll_merge could be + * wrong if we renamed from a->path to b->path. We should use the + * target path for where the file will be written. + */ + merge_status = ll_merge(result_buf, a->path, &orig, base, + &src1, name1, &src2, name2, + opt->repo->index, &ll_opts); + if (merge_status == LL_MERGE_BINARY_CONFLICT) + warning("Cannot merge binary files: %s (%s vs. %s)", + a->path, name1, name2); + + free(base); + free(name1); + free(name2); + free(orig.ptr); + free(src1.ptr); + free(src2.ptr); + return merge_status; +} + +static int find_first_merges(struct repository *repo, + struct object_array *result, const char *path, + struct commit *a, struct commit *b) +{ + int i, j; + struct object_array merges = OBJECT_ARRAY_INIT; + struct commit *commit; + int contains_another; + + char merged_revision[GIT_MAX_HEXSZ + 2]; + const char *rev_args[] = { "rev-list", "--merges", "--ancestry-path", + "--all", merged_revision, NULL }; + struct rev_info revs; + struct setup_revision_opt rev_opts; + + memset(result, 0, sizeof(struct object_array)); + memset(&rev_opts, 0, sizeof(rev_opts)); + + /* get all revisions that merge commit a */ + xsnprintf(merged_revision, sizeof(merged_revision), "^%s", + oid_to_hex(&a->object.oid)); + repo_init_revisions(repo, &revs, NULL); + /* FIXME: can't handle linked worktrees in submodules yet */ + revs.single_worktree = path != NULL; + setup_revisions(ARRAY_SIZE(rev_args)-1, rev_args, &revs, &rev_opts); + + /* save all revisions from the above list that contain b */ + if (prepare_revision_walk(&revs)) + die("revision walk setup failed"); + while ((commit = get_revision(&revs)) != NULL) { + struct object *o = &(commit->object); + int ret = repo_in_merge_bases(repo, b, commit); + if (ret < 0) { + object_array_clear(&merges); + release_revisions(&revs); + return ret; + } + if (ret) + add_object_array(o, NULL, &merges); + } + reset_revision_walk(); + + /* Now we've got all merges that contain a and b. Prune all + * merges that contain another found merge and save them in + * result. + */ + for (i = 0; i < merges.nr; i++) { + struct commit *m1 = (struct commit *) merges.objects[i].item; + + contains_another = 0; + for (j = 0; j < merges.nr; j++) { + struct commit *m2 = (struct commit *) merges.objects[j].item; + if (i != j) { + int ret = repo_in_merge_bases(repo, m2, m1); + if (ret < 0) { + object_array_clear(&merges); + release_revisions(&revs); + return ret; + } + if (ret > 0) { + contains_another = 1; + break; + } + } + } + + if (!contains_another) + add_object_array(merges.objects[i].item, NULL, result); + } + + object_array_clear(&merges); + release_revisions(&revs); + return result->nr; +} + +static void print_commit(struct repository *repo, struct commit *commit) +{ + struct strbuf sb = STRBUF_INIT; + struct pretty_print_context ctx = {0}; + ctx.date_mode.type = DATE_NORMAL; + /* FIXME: Merge this with output_commit_title() */ + assert(!merge_remote_util(commit)); + repo_format_commit_message(repo, commit, " %h: %m %s", &sb, &ctx); + fprintf(stderr, "%s\n", sb.buf); + strbuf_release(&sb); +} + +static int is_valid(const struct diff_filespec *dfs) +{ + return dfs->mode != 0 && !is_null_oid(&dfs->oid); +} + +static int merge_submodule(struct merge_options *opt, + struct object_id *result, const char *path, + const struct object_id *base, const struct object_id *a, + const struct object_id *b) +{ + struct repository subrepo; + int ret = 0, ret2; + struct commit *commit_base, *commit_a, *commit_b; + int parent_count; + struct object_array merges; + + int i; + int search = !opt->priv->call_depth; + + /* store a in result in case we fail */ + /* FIXME: This is the WRONG resolution for the recursive case when + * we need to be careful to avoid accidentally matching either side. + * Should probably use o instead there, much like we do for merging + * binaries. + */ + oidcpy(result, a); + + /* we can not handle deletion conflicts */ + if (is_null_oid(base)) + return 0; + if (is_null_oid(a)) + return 0; + if (is_null_oid(b)) + return 0; + + if (repo_submodule_init(&subrepo, opt->repo, path, null_oid(the_hash_algo))) { + output(opt, 1, _("Failed to merge submodule %s (not checked out)"), path); + return 0; + } + + if (!(commit_base = lookup_commit_reference(&subrepo, base)) || + !(commit_a = lookup_commit_reference(&subrepo, a)) || + !(commit_b = lookup_commit_reference(&subrepo, b))) { + output(opt, 1, _("Failed to merge submodule %s (commits not present)"), path); + goto cleanup; + } + + /* check whether both changes are forward */ + ret2 = repo_in_merge_bases(&subrepo, commit_base, commit_a); + if (ret2 < 0) { + output(opt, 1, _("Failed to merge submodule %s (repository corrupt)"), path); + ret = -1; + goto cleanup; + } + if (ret2 > 0) + ret2 = repo_in_merge_bases(&subrepo, commit_base, commit_b); + if (ret2 < 0) { + output(opt, 1, _("Failed to merge submodule %s (repository corrupt)"), path); + ret = -1; + goto cleanup; + } + if (!ret2) { + output(opt, 1, _("Failed to merge submodule %s (commits don't follow merge-base)"), path); + goto cleanup; + } + + /* Case #1: a is contained in b or vice versa */ + ret2 = repo_in_merge_bases(&subrepo, commit_a, commit_b); + if (ret2 < 0) { + output(opt, 1, _("Failed to merge submodule %s (repository corrupt)"), path); + ret = -1; + goto cleanup; + } + if (ret2) { + oidcpy(result, b); + if (show(opt, 3)) { + output(opt, 3, _("Fast-forwarding submodule %s to the following commit:"), path); + repo_output_commit_title(opt, &subrepo, commit_b); + } else if (show(opt, 2)) + output(opt, 2, _("Fast-forwarding submodule %s"), path); + else + ; /* no output */ + + ret = 1; + goto cleanup; + } + ret2 = repo_in_merge_bases(&subrepo, commit_b, commit_a); + if (ret2 < 0) { + output(opt, 1, _("Failed to merge submodule %s (repository corrupt)"), path); + ret = -1; + goto cleanup; + } + if (ret2) { + oidcpy(result, a); + if (show(opt, 3)) { + output(opt, 3, _("Fast-forwarding submodule %s to the following commit:"), path); + repo_output_commit_title(opt, &subrepo, commit_a); + } else if (show(opt, 2)) + output(opt, 2, _("Fast-forwarding submodule %s"), path); + else + ; /* no output */ + + ret = 1; + goto cleanup; + } + + /* + * Case #2: There are one or more merges that contain a and b in + * the submodule. If there is only one, then present it as a + * suggestion to the user, but leave it marked unmerged so the + * user needs to confirm the resolution. + */ + + /* Skip the search if makes no sense to the calling context. */ + if (!search) + goto cleanup; + + /* find commit which merges them */ + parent_count = find_first_merges(&subrepo, &merges, path, + commit_a, commit_b); + switch (parent_count) { + case -1: + output(opt, 1,_("Failed to merge submodule %s (repository corrupt)"), path); + ret = -1; + break; + case 0: + output(opt, 1, _("Failed to merge submodule %s (merge following commits not found)"), path); + break; + + case 1: + output(opt, 1, _("Failed to merge submodule %s (not fast-forward)"), path); + output(opt, 2, _("Found a possible merge resolution for the submodule:\n")); + print_commit(&subrepo, (struct commit *) merges.objects[0].item); + output(opt, 2, _( + "If this is correct simply add it to the index " + "for example\n" + "by using:\n\n" + " git update-index --cacheinfo 160000 %s \"%s\"\n\n" + "which will accept this suggestion.\n"), + oid_to_hex(&merges.objects[0].item->oid), path); + break; + + default: + output(opt, 1, _("Failed to merge submodule %s (multiple merges found)"), path); + for (i = 0; i < merges.nr; i++) + print_commit(&subrepo, (struct commit *) merges.objects[i].item); + } + + object_array_clear(&merges); +cleanup: + repo_clear(&subrepo); + return ret; +} + +static int merge_mode_and_contents(struct merge_options *opt, + const struct diff_filespec *o, + const struct diff_filespec *a, + const struct diff_filespec *b, + const char *filename, + const char *branch1, + const char *branch2, + const int extra_marker_size, + struct merge_file_info *result) +{ + if (opt->branch1 != branch1) { + /* + * It's weird getting a reverse merge with HEAD on the bottom + * side of the conflict markers and the other branch on the + * top. Fix that. + */ + return merge_mode_and_contents(opt, o, b, a, + filename, + branch2, branch1, + extra_marker_size, result); + } + + result->merge = 0; + result->clean = 1; + + if ((S_IFMT & a->mode) != (S_IFMT & b->mode)) { + result->clean = 0; + /* + * FIXME: This is a bad resolution for recursive case; for + * the recursive case we want something that is unlikely to + * accidentally match either side. Also, while it makes + * sense to prefer regular files over symlinks, it doesn't + * make sense to prefer regular files over submodules. + */ + if (S_ISREG(a->mode)) { + result->blob.mode = a->mode; + oidcpy(&result->blob.oid, &a->oid); + } else { + result->blob.mode = b->mode; + oidcpy(&result->blob.oid, &b->oid); + } + } else { + if (!oideq(&a->oid, &o->oid) && !oideq(&b->oid, &o->oid)) + result->merge = 1; + + /* + * Merge modes + */ + if (a->mode == b->mode || a->mode == o->mode) + result->blob.mode = b->mode; + else { + result->blob.mode = a->mode; + if (b->mode != o->mode) { + result->clean = 0; + result->merge = 1; + } + } + + if (oideq(&a->oid, &b->oid) || oideq(&a->oid, &o->oid)) + oidcpy(&result->blob.oid, &b->oid); + else if (oideq(&b->oid, &o->oid)) + oidcpy(&result->blob.oid, &a->oid); + else if (S_ISREG(a->mode)) { + mmbuffer_t result_buf; + int ret = 0, merge_status; + + merge_status = merge_3way(opt, &result_buf, o, a, b, + branch1, branch2, + extra_marker_size); + + if ((merge_status < 0) || !result_buf.ptr) + ret = err(opt, _("failed to execute internal merge")); + + if (!ret && + write_object_file(result_buf.ptr, result_buf.size, + OBJ_BLOB, &result->blob.oid)) + ret = err(opt, _("unable to add %s to database"), + a->path); + + free(result_buf.ptr); + if (ret) + return ret; + /* FIXME: bug, what if modes didn't match? */ + result->clean = (merge_status == 0); + } else if (S_ISGITLINK(a->mode)) { + int clean = merge_submodule(opt, &result->blob.oid, + o->path, + &o->oid, + &a->oid, + &b->oid); + if (clean < 0) + return -1; + result->clean = clean; + } else if (S_ISLNK(a->mode)) { + switch (opt->recursive_variant) { + case MERGE_VARIANT_NORMAL: + oidcpy(&result->blob.oid, &a->oid); + if (!oideq(&a->oid, &b->oid)) + result->clean = 0; + break; + case MERGE_VARIANT_OURS: + oidcpy(&result->blob.oid, &a->oid); + break; + case MERGE_VARIANT_THEIRS: + oidcpy(&result->blob.oid, &b->oid); + break; + } + } else + BUG("unsupported object type in the tree"); + } + + if (result->merge) + output(opt, 2, _("Auto-merging %s"), filename); + + return 0; +} + +static int handle_rename_via_dir(struct merge_options *opt, + struct rename_conflict_info *ci) +{ + /* + * Handle file adds that need to be renamed due to directory rename + * detection. This differs from handle_rename_normal, because + * there is no content merge to do; just move the file into the + * desired final location. + */ + const struct rename *ren = ci->ren1; + const struct diff_filespec *dest = ren->pair->two; + char *file_path = dest->path; + int mark_conflicted = (opt->detect_directory_renames == + MERGE_DIRECTORY_RENAMES_CONFLICT); + assert(ren->dir_rename_original_dest); + + if (!opt->priv->call_depth && would_lose_untracked(opt, dest->path)) { + mark_conflicted = 1; + file_path = unique_path(opt, dest->path, ren->branch); + output(opt, 1, _("Error: Refusing to lose untracked file at %s; " + "writing to %s instead."), + dest->path, file_path); + } + + if (mark_conflicted) { + /* + * Write the file in worktree at file_path. In the index, + * only record the file at dest->path in the appropriate + * higher stage. + */ + if (update_file(opt, 0, dest, file_path)) + return -1; + if (file_path != dest->path) + free(file_path); + if (update_stages(opt, dest->path, NULL, + ren->branch == opt->branch1 ? dest : NULL, + ren->branch == opt->branch1 ? NULL : dest)) + return -1; + return 0; /* not clean, but conflicted */ + } else { + /* Update dest->path both in index and in worktree */ + if (update_file(opt, 1, dest, dest->path)) + return -1; + return 1; /* clean */ + } +} + +static int handle_change_delete(struct merge_options *opt, + const char *path, const char *old_path, + const struct diff_filespec *o, + const struct diff_filespec *changed, + const char *change_branch, + const char *delete_branch, + const char *change, const char *change_past) +{ + char *alt_path = NULL; + const char *update_path = path; + int ret = 0; + + if (dir_in_way(opt->repo->index, path, !opt->priv->call_depth, 0) || + (!opt->priv->call_depth && would_lose_untracked(opt, path))) { + update_path = alt_path = unique_path(opt, path, change_branch); + } + + if (opt->priv->call_depth) { + /* + * We cannot arbitrarily accept either a_sha or b_sha as + * correct; since there is no true "middle point" between + * them, simply reuse the base version for virtual merge base. + */ + ret = remove_file_from_index(opt->repo->index, path); + if (!ret) + ret = update_file(opt, 0, o, update_path); + } else { + /* + * Despite the four nearly duplicate messages and argument + * lists below and the ugliness of the nested if-statements, + * having complete messages makes the job easier for + * translators. + * + * The slight variance among the cases is due to the fact + * that: + * 1) directory/file conflicts (in effect if + * !alt_path) could cause us to need to write the + * file to a different path. + * 2) renames (in effect if !old_path) could mean that + * there are two names for the path that the user + * may know the file by. + */ + if (!alt_path) { + if (!old_path) { + output(opt, 1, _("CONFLICT (%s/delete): %s deleted in %s " + "and %s in %s. Version %s of %s left in tree."), + change, path, delete_branch, change_past, + change_branch, change_branch, path); + } else { + output(opt, 1, _("CONFLICT (%s/delete): %s deleted in %s " + "and %s to %s in %s. Version %s of %s left in tree."), + change, old_path, delete_branch, change_past, path, + change_branch, change_branch, path); + } + } else { + if (!old_path) { + output(opt, 1, _("CONFLICT (%s/delete): %s deleted in %s " + "and %s in %s. Version %s of %s left in tree at %s."), + change, path, delete_branch, change_past, + change_branch, change_branch, path, alt_path); + } else { + output(opt, 1, _("CONFLICT (%s/delete): %s deleted in %s " + "and %s to %s in %s. Version %s of %s left in tree at %s."), + change, old_path, delete_branch, change_past, path, + change_branch, change_branch, path, alt_path); + } + } + /* + * No need to call update_file() on path when change_branch == + * opt->branch1 && !alt_path, since that would needlessly touch + * path. We could call update_file_flags() with update_cache=0 + * and update_wd=0, but that's a no-op. + */ + if (change_branch != opt->branch1 || alt_path) + ret = update_file(opt, 0, changed, update_path); + } + free(alt_path); + + return ret; +} + +static int handle_rename_delete(struct merge_options *opt, + struct rename_conflict_info *ci) +{ + const struct rename *ren = ci->ren1; + const struct diff_filespec *orig = ren->pair->one; + const struct diff_filespec *dest = ren->pair->two; + const char *rename_branch = ren->branch; + const char *delete_branch = (opt->branch1 == ren->branch ? + opt->branch2 : opt->branch1); + + if (handle_change_delete(opt, + opt->priv->call_depth ? orig->path : dest->path, + opt->priv->call_depth ? NULL : orig->path, + orig, dest, + rename_branch, delete_branch, + _("rename"), _("renamed"))) + return -1; + + if (opt->priv->call_depth) + return remove_file_from_index(opt->repo->index, dest->path); + else + return update_stages(opt, dest->path, NULL, + rename_branch == opt->branch1 ? dest : NULL, + rename_branch == opt->branch1 ? NULL : dest); +} + +static int handle_file_collision(struct merge_options *opt, + const char *collide_path, + const char *prev_path1, + const char *prev_path2, + const char *branch1, const char *branch2, + struct diff_filespec *a, + struct diff_filespec *b) +{ + struct merge_file_info mfi; + struct diff_filespec null; + char *alt_path = NULL; + const char *update_path = collide_path; + + /* + * It's easiest to get the correct things into stage 2 and 3, and + * to make sure that the content merge puts HEAD before the other + * branch if we just ensure that branch1 == opt->branch1. So, simply + * flip arguments around if we don't have that. + */ + if (branch1 != opt->branch1) { + return handle_file_collision(opt, collide_path, + prev_path2, prev_path1, + branch2, branch1, + b, a); + } + + /* Remove rename sources if rename/add or rename/rename(2to1) */ + if (prev_path1) + remove_file(opt, 1, prev_path1, + opt->priv->call_depth || would_lose_untracked(opt, prev_path1)); + if (prev_path2) + remove_file(opt, 1, prev_path2, + opt->priv->call_depth || would_lose_untracked(opt, prev_path2)); + + /* + * Remove the collision path, if it wouldn't cause dirty contents + * or an untracked file to get lost. We'll either overwrite with + * merged contents, or just write out to differently named files. + */ + if (was_dirty(opt, collide_path)) { + output(opt, 1, _("Refusing to lose dirty file at %s"), + collide_path); + update_path = alt_path = unique_path(opt, collide_path, "merged"); + } else if (would_lose_untracked(opt, collide_path)) { + /* + * Only way we get here is if both renames were from + * a directory rename AND user had an untracked file + * at the location where both files end up after the + * two directory renames. See testcase 10d of t6043. + */ + output(opt, 1, _("Refusing to lose untracked file at " + "%s, even though it's in the way."), + collide_path); + update_path = alt_path = unique_path(opt, collide_path, "merged"); + } else { + /* + * FIXME: It's possible that the two files are identical + * and that the current working copy happens to match, in + * which case we are unnecessarily touching the working + * tree file. It's not a likely enough scenario that I + * want to code up the checks for it and a better fix is + * available if we restructure how unpack_trees() and + * merge-recursive interoperate anyway, so punting for + * now... + */ + remove_file(opt, 0, collide_path, 0); + } + + /* Store things in diff_filespecs for functions that need it */ + null.path = (char *)collide_path; + oidcpy(&null.oid, null_oid(the_hash_algo)); + null.mode = 0; + + if (merge_mode_and_contents(opt, &null, a, b, collide_path, + branch1, branch2, opt->priv->call_depth * 2, &mfi)) + return -1; + mfi.clean &= !alt_path; + if (update_file(opt, mfi.clean, &mfi.blob, update_path)) + return -1; + if (!mfi.clean && !opt->priv->call_depth && + update_stages(opt, collide_path, NULL, a, b)) + return -1; + free(alt_path); + /* + * FIXME: If both a & b both started with conflicts (only possible + * if they came from a rename/rename(2to1)), but had IDENTICAL + * contents including those conflicts, then in the next line we claim + * it was clean. If someone cares about this case, we should have the + * caller notify us if we started with conflicts. + */ + return mfi.clean; +} + +static int handle_rename_add(struct merge_options *opt, + struct rename_conflict_info *ci) +{ + /* a was renamed to c, and a separate c was added. */ + struct diff_filespec *a = ci->ren1->pair->one; + struct diff_filespec *c = ci->ren1->pair->two; + char *path = c->path; + char *prev_path_desc; + struct merge_file_info mfi; + + const char *rename_branch = ci->ren1->branch; + const char *add_branch = (opt->branch1 == rename_branch ? + opt->branch2 : opt->branch1); + int other_stage = (ci->ren1->branch == opt->branch1 ? 3 : 2); + + output(opt, 1, _("CONFLICT (rename/add): " + "Rename %s->%s in %s. Added %s in %s"), + a->path, c->path, rename_branch, + c->path, add_branch); + + prev_path_desc = xstrfmt("version of %s from %s", path, a->path); + ci->ren1->src_entry->stages[other_stage].path = a->path; + if (merge_mode_and_contents(opt, a, c, + &ci->ren1->src_entry->stages[other_stage], + prev_path_desc, + opt->branch1, opt->branch2, + 1 + opt->priv->call_depth * 2, &mfi)) + return -1; + free(prev_path_desc); + + ci->ren1->dst_entry->stages[other_stage].path = mfi.blob.path = c->path; + return handle_file_collision(opt, + c->path, a->path, NULL, + rename_branch, add_branch, + &mfi.blob, + &ci->ren1->dst_entry->stages[other_stage]); +} + +static char *find_path_for_conflict(struct merge_options *opt, + const char *path, + const char *branch1, + const char *branch2) +{ + char *new_path = NULL; + if (dir_in_way(opt->repo->index, path, !opt->priv->call_depth, 0)) { + new_path = unique_path(opt, path, branch1); + output(opt, 1, _("%s is a directory in %s adding " + "as %s instead"), + path, branch2, new_path); + } else if (would_lose_untracked(opt, path)) { + new_path = unique_path(opt, path, branch1); + output(opt, 1, _("Refusing to lose untracked file" + " at %s; adding as %s instead"), + path, new_path); + } + + return new_path; +} + +/* + * Toggle the stage number between "ours" and "theirs" (2 and 3). + */ +static inline int flip_stage(int stage) +{ + return (2 + 3) - stage; +} + +static int handle_rename_rename_1to2(struct merge_options *opt, + struct rename_conflict_info *ci) +{ + /* One file was renamed in both branches, but to different names. */ + struct merge_file_info mfi; + struct diff_filespec *add; + struct diff_filespec *o = ci->ren1->pair->one; + struct diff_filespec *a = ci->ren1->pair->two; + struct diff_filespec *b = ci->ren2->pair->two; + char *path_desc; + + output(opt, 1, _("CONFLICT (rename/rename): " + "Rename \"%s\"->\"%s\" in branch \"%s\" " + "rename \"%s\"->\"%s\" in \"%s\"%s"), + o->path, a->path, ci->ren1->branch, + o->path, b->path, ci->ren2->branch, + opt->priv->call_depth ? _(" (left unresolved)") : ""); + + path_desc = xstrfmt("%s and %s, both renamed from %s", + a->path, b->path, o->path); + if (merge_mode_and_contents(opt, o, a, b, path_desc, + ci->ren1->branch, ci->ren2->branch, + opt->priv->call_depth * 2, &mfi)) + return -1; + free(path_desc); + + if (opt->priv->call_depth) + remove_file_from_index(opt->repo->index, o->path); + + /* + * For each destination path, we need to see if there is a + * rename/add collision. If not, we can write the file out + * to the specified location. + */ + add = &ci->ren1->dst_entry->stages[flip_stage(2)]; + if (is_valid(add)) { + add->path = mfi.blob.path = a->path; + if (handle_file_collision(opt, a->path, + NULL, NULL, + ci->ren1->branch, + ci->ren2->branch, + &mfi.blob, add) < 0) + return -1; + } else { + char *new_path = find_path_for_conflict(opt, a->path, + ci->ren1->branch, + ci->ren2->branch); + if (update_file(opt, 0, &mfi.blob, + new_path ? new_path : a->path)) + return -1; + free(new_path); + if (!opt->priv->call_depth && + update_stages(opt, a->path, NULL, a, NULL)) + return -1; + } + + if (!mfi.clean && mfi.blob.mode == a->mode && + oideq(&mfi.blob.oid, &a->oid)) { + /* + * Getting here means we were attempting to merge a binary + * blob. Since we can't merge binaries, the merge algorithm + * just takes one side. But we don't want to copy the + * contents of one side to both paths; we'd rather use the + * original content at the given path for each path. + */ + oidcpy(&mfi.blob.oid, &b->oid); + mfi.blob.mode = b->mode; + } + add = &ci->ren2->dst_entry->stages[flip_stage(3)]; + if (is_valid(add)) { + add->path = mfi.blob.path = b->path; + if (handle_file_collision(opt, b->path, + NULL, NULL, + ci->ren1->branch, + ci->ren2->branch, + add, &mfi.blob) < 0) + return -1; + } else { + char *new_path = find_path_for_conflict(opt, b->path, + ci->ren2->branch, + ci->ren1->branch); + if (update_file(opt, 0, &mfi.blob, + new_path ? new_path : b->path)) + return -1; + free(new_path); + if (!opt->priv->call_depth && + update_stages(opt, b->path, NULL, NULL, b)) + return -1; + } + + return 0; +} + +static int handle_rename_rename_2to1(struct merge_options *opt, + struct rename_conflict_info *ci) +{ + /* Two files, a & b, were renamed to the same thing, c. */ + struct diff_filespec *a = ci->ren1->pair->one; + struct diff_filespec *b = ci->ren2->pair->one; + struct diff_filespec *c1 = ci->ren1->pair->two; + struct diff_filespec *c2 = ci->ren2->pair->two; + char *path = c1->path; /* == c2->path */ + char *path_side_1_desc; + char *path_side_2_desc; + struct merge_file_info mfi_c1; + struct merge_file_info mfi_c2; + int ostage1, ostage2; + + output(opt, 1, _("CONFLICT (rename/rename): " + "Rename %s->%s in %s. " + "Rename %s->%s in %s"), + a->path, c1->path, ci->ren1->branch, + b->path, c2->path, ci->ren2->branch); + + path_side_1_desc = xstrfmt("version of %s from %s", path, a->path); + path_side_2_desc = xstrfmt("version of %s from %s", path, b->path); + ostage1 = ci->ren1->branch == opt->branch1 ? 3 : 2; + ostage2 = flip_stage(ostage1); + ci->ren1->src_entry->stages[ostage1].path = a->path; + ci->ren2->src_entry->stages[ostage2].path = b->path; + if (merge_mode_and_contents(opt, a, c1, + &ci->ren1->src_entry->stages[ostage1], + path_side_1_desc, + opt->branch1, opt->branch2, + 1 + opt->priv->call_depth * 2, &mfi_c1) || + merge_mode_and_contents(opt, b, + &ci->ren2->src_entry->stages[ostage2], + c2, path_side_2_desc, + opt->branch1, opt->branch2, + 1 + opt->priv->call_depth * 2, &mfi_c2)) + return -1; + free(path_side_1_desc); + free(path_side_2_desc); + mfi_c1.blob.path = path; + mfi_c2.blob.path = path; + + return handle_file_collision(opt, path, a->path, b->path, + ci->ren1->branch, ci->ren2->branch, + &mfi_c1.blob, &mfi_c2.blob); +} + +/* + * Get the diff_filepairs changed between o_tree and tree. + */ +static struct diff_queue_struct *get_diffpairs(struct merge_options *opt, + struct tree *o_tree, + struct tree *tree) +{ + struct diff_queue_struct *ret; + struct diff_options opts; + + repo_diff_setup(opt->repo, &opts); + opts.flags.recursive = 1; + opts.flags.rename_empty = 0; + opts.detect_rename = merge_detect_rename(opt); + /* + * We do not have logic to handle the detection of copies. In + * fact, it may not even make sense to add such logic: would we + * really want a change to a base file to be propagated through + * multiple other files by a merge? + */ + if (opts.detect_rename > DIFF_DETECT_RENAME) + opts.detect_rename = DIFF_DETECT_RENAME; + opts.rename_limit = (opt->rename_limit >= 0) ? opt->rename_limit : 7000; + opts.rename_score = opt->rename_score; + opts.show_rename_progress = opt->show_rename_progress; + opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_setup_done(&opts); + diff_tree_oid(&o_tree->object.oid, &tree->object.oid, "", &opts); + diffcore_std(&opts); + if (opts.needed_rename_limit > opt->priv->needed_rename_limit) + opt->priv->needed_rename_limit = opts.needed_rename_limit; + + ret = xmalloc(sizeof(*ret)); + *ret = diff_queued_diff; + + opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_queued_diff.nr = 0; + diff_queued_diff.queue = NULL; + diff_flush(&opts); + return ret; +} + +static int tree_has_path(struct repository *r, struct tree *tree, + const char *path) +{ + struct object_id hashy; + unsigned short mode_o; + + return !get_tree_entry(r, + &tree->object.oid, path, + &hashy, &mode_o); +} + +/* + * Return a new string that replaces the beginning portion (which matches + * entry->dir), with entry->new_dir. In perl-speak: + * new_path_name = (old_path =~ s/entry->dir/entry->new_dir/); + * NOTE: + * Caller must ensure that old_path starts with entry->dir + '/'. + */ +static char *apply_dir_rename(struct dir_rename_entry *entry, + const char *old_path) +{ + struct strbuf new_path = STRBUF_INIT; + int oldlen, newlen; + + if (entry->non_unique_new_dir) + return NULL; + + oldlen = strlen(entry->dir); + if (entry->new_dir.len == 0) + /* + * If someone renamed/merged a subdirectory into the root + * directory (e.g. 'some/subdir' -> ''), then we want to + * avoid returning + * '' + '/filename' + * as the rename; we need to make old_path + oldlen advance + * past the '/' character. + */ + oldlen++; + newlen = entry->new_dir.len + (strlen(old_path) - oldlen) + 1; + strbuf_grow(&new_path, newlen); + strbuf_addbuf(&new_path, &entry->new_dir); + strbuf_addstr(&new_path, &old_path[oldlen]); + + return strbuf_detach(&new_path, NULL); +} + +static void get_renamed_dir_portion(const char *old_path, const char *new_path, + char **old_dir, char **new_dir) +{ + char *end_of_old, *end_of_new; + + /* Default return values: NULL, meaning no rename */ + *old_dir = NULL; + *new_dir = NULL; + + /* + * For + * "a/b/c/d/e/foo.c" -> "a/b/some/thing/else/e/foo.c" + * the "e/foo.c" part is the same, we just want to know that + * "a/b/c/d" was renamed to "a/b/some/thing/else" + * so, for this example, this function returns "a/b/c/d" in + * *old_dir and "a/b/some/thing/else" in *new_dir. + */ + + /* + * If the basename of the file changed, we don't care. We want + * to know which portion of the directory, if any, changed. + */ + end_of_old = strrchr(old_path, '/'); + end_of_new = strrchr(new_path, '/'); + + /* + * If end_of_old is NULL, old_path wasn't in a directory, so there + * could not be a directory rename (our rule elsewhere that a + * directory which still exists is not considered to have been + * renamed means the root directory can never be renamed -- because + * the root directory always exists). + */ + if (!end_of_old) + return; /* Note: *old_dir and *new_dir are still NULL */ + + /* + * If new_path contains no directory (end_of_new is NULL), then we + * have a rename of old_path's directory to the root directory. + */ + if (!end_of_new) { + *old_dir = xstrndup(old_path, end_of_old - old_path); + *new_dir = xstrdup(""); + return; + } + + /* Find the first non-matching character traversing backwards */ + while (*--end_of_new == *--end_of_old && + end_of_old != old_path && + end_of_new != new_path) + ; /* Do nothing; all in the while loop */ + + /* + * If both got back to the beginning of their strings, then the + * directory didn't change at all, only the basename did. + */ + if (end_of_old == old_path && end_of_new == new_path && + *end_of_old == *end_of_new) + return; /* Note: *old_dir and *new_dir are still NULL */ + + /* + * If end_of_new got back to the beginning of its string, and + * end_of_old got back to the beginning of some subdirectory, then + * we have a rename/merge of a subdirectory into the root, which + * needs slightly special handling. + * + * Note: There is no need to consider the opposite case, with a + * rename/merge of the root directory into some subdirectory + * because as noted above the root directory always exists so it + * cannot be considered to be renamed. + */ + if (end_of_new == new_path && + end_of_old != old_path && end_of_old[-1] == '/') { + *old_dir = xstrndup(old_path, --end_of_old - old_path); + *new_dir = xstrdup(""); + return; + } + + /* + * We've found the first non-matching character in the directory + * paths. That means the current characters we were looking at + * were part of the first non-matching subdir name going back from + * the end of the strings. Get the whole name by advancing both + * end_of_old and end_of_new to the NEXT '/' character. That will + * represent the entire directory rename. + * + * The reason for the increment is cases like + * a/b/star/foo/whatever.c -> a/b/tar/foo/random.c + * After dropping the basename and going back to the first + * non-matching character, we're now comparing: + * a/b/s and a/b/ + * and we want to be comparing: + * a/b/star/ and a/b/tar/ + * but without the pre-increment, the one on the right would stay + * a/b/. + */ + end_of_old = strchr(++end_of_old, '/'); + end_of_new = strchr(++end_of_new, '/'); + + /* Copy the old and new directories into *old_dir and *new_dir. */ + *old_dir = xstrndup(old_path, end_of_old - old_path); + *new_dir = xstrndup(new_path, end_of_new - new_path); +} + +static void remove_hashmap_entries(struct hashmap *dir_renames, + struct string_list *items_to_remove) +{ + int i; + struct dir_rename_entry *entry; + + for (i = 0; i < items_to_remove->nr; i++) { + entry = items_to_remove->items[i].util; + hashmap_remove(dir_renames, &entry->ent, NULL); + } + string_list_clear(items_to_remove, 0); +} + +/* + * See if there is a directory rename for path, and if there are any file + * level conflicts for the renamed location. If there is a rename and + * there are no conflicts, return the new name. Otherwise, return NULL. + */ +static char *handle_path_level_conflicts(struct merge_options *opt, + const char *path, + struct dir_rename_entry *entry, + struct hashmap *collisions, + struct tree *tree) +{ + char *new_path = NULL; + struct collision_entry *collision_ent; + int clean = 1; + struct strbuf collision_paths = STRBUF_INIT; + + /* + * entry has the mapping of old directory name to new directory name + * that we want to apply to path. + */ + new_path = apply_dir_rename(entry, path); + + if (!new_path) { + /* This should only happen when entry->non_unique_new_dir set */ + if (!entry->non_unique_new_dir) + BUG("entry->non_unique_new_dir not set and !new_path"); + output(opt, 1, _("CONFLICT (directory rename split): " + "Unclear where to place %s because directory " + "%s was renamed to multiple other directories, " + "with no destination getting a majority of the " + "files."), + path, entry->dir); + clean = 0; + return NULL; + } + + /* + * The caller needs to have ensured that it has pre-populated + * collisions with all paths that map to new_path. Do a quick check + * to ensure that's the case. + */ + collision_ent = collision_find_entry(collisions, new_path); + if (!collision_ent) + BUG("collision_ent is NULL"); + + /* + * Check for one-sided add/add/.../add conflicts, i.e. + * where implicit renames from the other side doing + * directory rename(s) can affect this side of history + * to put multiple paths into the same location. Warn + * and bail on directory renames for such paths. + */ + if (collision_ent->reported_already) { + clean = 0; + } else if (tree_has_path(opt->repo, tree, new_path)) { + collision_ent->reported_already = 1; + strbuf_add_separated_string_list(&collision_paths, ", ", + &collision_ent->source_files); + output(opt, 1, _("CONFLICT (implicit dir rename): Existing " + "file/dir at %s in the way of implicit " + "directory rename(s) putting the following " + "path(s) there: %s."), + new_path, collision_paths.buf); + clean = 0; + } else if (collision_ent->source_files.nr > 1) { + collision_ent->reported_already = 1; + strbuf_add_separated_string_list(&collision_paths, ", ", + &collision_ent->source_files); + output(opt, 1, _("CONFLICT (implicit dir rename): Cannot map " + "more than one path to %s; implicit directory " + "renames tried to put these paths there: %s"), + new_path, collision_paths.buf); + clean = 0; + } + + /* Free memory we no longer need */ + strbuf_release(&collision_paths); + if (!clean && new_path) { + free(new_path); + return NULL; + } + + return new_path; +} + +/* + * There are a couple things we want to do at the directory level: + * 1. Check for both sides renaming to the same thing, in order to avoid + * implicit renaming of files that should be left in place. (See + * testcase 6b in t6043 for details.) + * 2. Prune directory renames if there are still files left in the + * original directory. These represent a partial directory rename, + * i.e. a rename where only some of the files within the directory + * were renamed elsewhere. (Technically, this could be done earlier + * in get_directory_renames(), except that would prevent us from + * doing the previous check and thus failing testcase 6b.) + * 3. Check for rename/rename(1to2) conflicts (at the directory level). + * In the future, we could potentially record this info as well and + * omit reporting rename/rename(1to2) conflicts for each path within + * the affected directories, thus cleaning up the merge output. + * NOTE: We do NOT check for rename/rename(2to1) conflicts at the + * directory level, because merging directories is fine. If it + * causes conflicts for files within those merged directories, then + * that should be detected at the individual path level. + */ +static void handle_directory_level_conflicts(struct merge_options *opt, + struct hashmap *dir_re_head, + struct tree *head, + struct hashmap *dir_re_merge, + struct tree *merge) +{ + struct hashmap_iter iter; + struct dir_rename_entry *head_ent; + struct dir_rename_entry *merge_ent; + + struct string_list remove_from_head = STRING_LIST_INIT_NODUP; + struct string_list remove_from_merge = STRING_LIST_INIT_NODUP; + + hashmap_for_each_entry(dir_re_head, &iter, head_ent, + ent /* member name */) { + merge_ent = dir_rename_find_entry(dir_re_merge, head_ent->dir); + if (merge_ent && + !head_ent->non_unique_new_dir && + !merge_ent->non_unique_new_dir && + !strbuf_cmp(&head_ent->new_dir, &merge_ent->new_dir)) { + /* 1. Renamed identically; remove it from both sides */ + string_list_append(&remove_from_head, + head_ent->dir)->util = head_ent; + strbuf_release(&head_ent->new_dir); + string_list_append(&remove_from_merge, + merge_ent->dir)->util = merge_ent; + strbuf_release(&merge_ent->new_dir); + } else if (tree_has_path(opt->repo, head, head_ent->dir)) { + /* 2. This wasn't a directory rename after all */ + string_list_append(&remove_from_head, + head_ent->dir)->util = head_ent; + strbuf_release(&head_ent->new_dir); + } + } + + remove_hashmap_entries(dir_re_head, &remove_from_head); + remove_hashmap_entries(dir_re_merge, &remove_from_merge); + + hashmap_for_each_entry(dir_re_merge, &iter, merge_ent, + ent /* member name */) { + head_ent = dir_rename_find_entry(dir_re_head, merge_ent->dir); + if (tree_has_path(opt->repo, merge, merge_ent->dir)) { + /* 2. This wasn't a directory rename after all */ + string_list_append(&remove_from_merge, + merge_ent->dir)->util = merge_ent; + } else if (head_ent && + !head_ent->non_unique_new_dir && + !merge_ent->non_unique_new_dir) { + /* 3. rename/rename(1to2) */ + /* + * We can assume it's not rename/rename(1to1) because + * that was case (1), already checked above. So we + * know that head_ent->new_dir and merge_ent->new_dir + * are different strings. + */ + output(opt, 1, _("CONFLICT (rename/rename): " + "Rename directory %s->%s in %s. " + "Rename directory %s->%s in %s"), + head_ent->dir, head_ent->new_dir.buf, opt->branch1, + head_ent->dir, merge_ent->new_dir.buf, opt->branch2); + string_list_append(&remove_from_head, + head_ent->dir)->util = head_ent; + strbuf_release(&head_ent->new_dir); + string_list_append(&remove_from_merge, + merge_ent->dir)->util = merge_ent; + strbuf_release(&merge_ent->new_dir); + } + } + + remove_hashmap_entries(dir_re_head, &remove_from_head); + remove_hashmap_entries(dir_re_merge, &remove_from_merge); +} + +static struct hashmap *get_directory_renames(struct diff_queue_struct *pairs) +{ + struct hashmap *dir_renames; + struct hashmap_iter iter; + struct dir_rename_entry *entry; + int i; + + /* + * Typically, we think of a directory rename as all files from a + * certain directory being moved to a target directory. However, + * what if someone first moved two files from the original + * directory in one commit, and then renamed the directory + * somewhere else in a later commit? At merge time, we just know + * that files from the original directory went to two different + * places, and that the bulk of them ended up in the same place. + * We want each directory rename to represent where the bulk of the + * files from that directory end up; this function exists to find + * where the bulk of the files went. + * + * The first loop below simply iterates through the list of file + * renames, finding out how often each directory rename pair + * possibility occurs. + */ + dir_renames = xmalloc(sizeof(*dir_renames)); + dir_rename_init(dir_renames); + for (i = 0; i < pairs->nr; ++i) { + struct string_list_item *item; + int *count; + struct diff_filepair *pair = pairs->queue[i]; + char *old_dir, *new_dir; + + /* File not part of directory rename if it wasn't renamed */ + if (pair->status != 'R') + continue; + + get_renamed_dir_portion(pair->one->path, pair->two->path, + &old_dir, &new_dir); + if (!old_dir) + /* Directory didn't change at all; ignore this one. */ + continue; + + entry = dir_rename_find_entry(dir_renames, old_dir); + if (!entry) { + entry = xmalloc(sizeof(*entry)); + dir_rename_entry_init(entry, old_dir); + hashmap_put(dir_renames, &entry->ent); + } else { + free(old_dir); + } + item = string_list_lookup(&entry->possible_new_dirs, new_dir); + if (!item) { + item = string_list_insert(&entry->possible_new_dirs, + new_dir); + item->util = xcalloc(1, sizeof(int)); + } else { + free(new_dir); + } + count = item->util; + *count += 1; + } + + /* + * For each directory with files moved out of it, we find out which + * target directory received the most files so we can declare it to + * be the "winning" target location for the directory rename. This + * winner gets recorded in new_dir. If there is no winner + * (multiple target directories received the same number of files), + * we set non_unique_new_dir. Once we've determined the winner (or + * that there is no winner), we no longer need possible_new_dirs. + */ + hashmap_for_each_entry(dir_renames, &iter, entry, + ent /* member name */) { + int max = 0; + int bad_max = 0; + char *best = NULL; + + for (i = 0; i < entry->possible_new_dirs.nr; i++) { + int *count = entry->possible_new_dirs.items[i].util; + + if (*count == max) + bad_max = max; + else if (*count > max) { + max = *count; + best = entry->possible_new_dirs.items[i].string; + } + } + if (bad_max == max) + entry->non_unique_new_dir = 1; + else { + assert(entry->new_dir.len == 0); + strbuf_addstr(&entry->new_dir, best); + } + /* + * The relevant directory sub-portion of the original full + * filepaths were xstrndup'ed before inserting into + * possible_new_dirs, and instead of manually iterating the + * list and free'ing each, just lie and tell + * possible_new_dirs that it did the strdup'ing so that it + * will free them for us. + */ + entry->possible_new_dirs.strdup_strings = 1; + string_list_clear(&entry->possible_new_dirs, 1); + } + + return dir_renames; +} + +static struct dir_rename_entry *check_dir_renamed(const char *path, + struct hashmap *dir_renames) +{ + char *temp = xstrdup(path); + char *end; + struct dir_rename_entry *entry = NULL; + + while ((end = strrchr(temp, '/'))) { + *end = '\0'; + entry = dir_rename_find_entry(dir_renames, temp); + if (entry) + break; + } + free(temp); + return entry; +} + +static void compute_collisions(struct hashmap *collisions, + struct hashmap *dir_renames, + struct diff_queue_struct *pairs) +{ + int i; + + /* + * Multiple files can be mapped to the same path due to directory + * renames done by the other side of history. Since that other + * side of history could have merged multiple directories into one, + * if our side of history added the same file basename to each of + * those directories, then all N of them would get implicitly + * renamed by the directory rename detection into the same path, + * and we'd get an add/add/.../add conflict, and all those adds + * from *this* side of history. This is not representable in the + * index, and users aren't going to easily be able to make sense of + * it. So we need to provide a good warning about what's + * happening, and fall back to no-directory-rename detection + * behavior for those paths. + * + * See testcases 9e and all of section 5 from t6043 for examples. + */ + collision_init(collisions); + + for (i = 0; i < pairs->nr; ++i) { + struct dir_rename_entry *dir_rename_ent; + struct collision_entry *collision_ent; + char *new_path; + struct diff_filepair *pair = pairs->queue[i]; + + if (pair->status != 'A' && pair->status != 'R') + continue; + dir_rename_ent = check_dir_renamed(pair->two->path, + dir_renames); + if (!dir_rename_ent) + continue; + + new_path = apply_dir_rename(dir_rename_ent, pair->two->path); + if (!new_path) + /* + * dir_rename_ent->non_unique_new_path is true, which + * means there is no directory rename for us to use, + * which means it won't cause us any additional + * collisions. + */ + continue; + collision_ent = collision_find_entry(collisions, new_path); + if (!collision_ent) { + CALLOC_ARRAY(collision_ent, 1); + hashmap_entry_init(&collision_ent->ent, + strhash(new_path)); + hashmap_put(collisions, &collision_ent->ent); + collision_ent->target_file = new_path; + } else { + free(new_path); + } + string_list_insert(&collision_ent->source_files, + pair->two->path); + } +} + +static char *check_for_directory_rename(struct merge_options *opt, + const char *path, + struct tree *tree, + struct hashmap *dir_renames, + struct hashmap *dir_rename_exclusions, + struct hashmap *collisions, + int *clean_merge) +{ + char *new_path = NULL; + struct dir_rename_entry *entry = check_dir_renamed(path, dir_renames); + struct dir_rename_entry *oentry = NULL; + + if (!entry) + return new_path; + + /* + * This next part is a little weird. We do not want to do an + * implicit rename into a directory we renamed on our side, because + * that will result in a spurious rename/rename(1to2) conflict. An + * example: + * Base commit: dumbdir/afile, otherdir/bfile + * Side 1: smrtdir/afile, otherdir/bfile + * Side 2: dumbdir/afile, dumbdir/bfile + * Here, while working on Side 1, we could notice that otherdir was + * renamed/merged to dumbdir, and change the diff_filepair for + * otherdir/bfile into a rename into dumbdir/bfile. However, Side + * 2 will notice the rename from dumbdir to smrtdir, and do the + * transitive rename to move it from dumbdir/bfile to + * smrtdir/bfile. That gives us bfile in dumbdir vs being in + * smrtdir, a rename/rename(1to2) conflict. We really just want + * the file to end up in smrtdir. And the way to achieve that is + * to not let Side1 do the rename to dumbdir, since we know that is + * the source of one of our directory renames. + * + * That's why oentry and dir_rename_exclusions is here. + * + * As it turns out, this also prevents N-way transient rename + * confusion; See testcases 9c and 9d of t6043. + */ + oentry = dir_rename_find_entry(dir_rename_exclusions, entry->new_dir.buf); + if (oentry) { + output(opt, 1, _("WARNING: Avoiding applying %s -> %s rename " + "to %s, because %s itself was renamed."), + entry->dir, entry->new_dir.buf, path, entry->new_dir.buf); + } else { + new_path = handle_path_level_conflicts(opt, path, entry, + collisions, tree); + *clean_merge &= (new_path != NULL); + } + + return new_path; +} + +static void apply_directory_rename_modifications(struct merge_options *opt, + struct diff_filepair *pair, + char *new_path, + struct rename *re, + struct tree *tree, + struct tree *o_tree, + struct tree *a_tree, + struct tree *b_tree, + struct string_list *entries) +{ + struct string_list_item *item; + int stage = (tree == a_tree ? 2 : 3); + int update_wd; + + /* + * In all cases where we can do directory rename detection, + * unpack_trees() will have read pair->two->path into the + * index and the working copy. We need to remove it so that + * we can instead place it at new_path. It is guaranteed to + * not be untracked (unpack_trees() would have errored out + * saying the file would have been overwritten), but it might + * be dirty, though. + */ + update_wd = !was_dirty(opt, pair->two->path); + if (!update_wd) + output(opt, 1, _("Refusing to lose dirty file at %s"), + pair->two->path); + remove_file(opt, 1, pair->two->path, !update_wd); + + /* Find or create a new re->dst_entry */ + item = string_list_lookup(entries, new_path); + if (item) { + /* + * Since we're renaming on this side of history, and it's + * due to a directory rename on the other side of history + * (which we only allow when the directory in question no + * longer exists on the other side of history), the + * original entry for re->dst_entry is no longer + * necessary... + */ + re->dst_entry->processed = 1; + + /* + * ...because we'll be using this new one. + */ + re->dst_entry = item->util; + } else { + /* + * re->dst_entry is for the before-dir-rename path, and we + * need it to hold information for the after-dir-rename + * path. Before creating a new entry, we need to mark the + * old one as unnecessary (...unless it is shared by + * src_entry, i.e. this didn't use to be a rename, in which + * case we can just allow the normal processing to happen + * for it). + */ + if (pair->status == 'R') + re->dst_entry->processed = 1; + + re->dst_entry = insert_stage_data(opt->repo, new_path, + o_tree, a_tree, b_tree, + entries); + item = string_list_insert(entries, new_path); + item->util = re->dst_entry; + } + + /* + * Update the stage_data with the information about the path we are + * moving into place. That slot will be empty and available for us + * to write to because of the collision checks in + * handle_path_level_conflicts(). In other words, + * re->dst_entry->stages[stage].oid will be the null_oid, so it's + * open for us to write to. + * + * It may be tempting to actually update the index at this point as + * well, using update_stages_for_stage_data(), but as per the big + * "NOTE" in update_stages(), doing so will modify the current + * in-memory index which will break calls to would_lose_untracked() + * that we need to make. Instead, we need to just make sure that + * the various handle_rename_*() functions update the index + * explicitly rather than relying on unpack_trees() to have done it. + */ + get_tree_entry(opt->repo, + &tree->object.oid, + pair->two->path, + &re->dst_entry->stages[stage].oid, + &re->dst_entry->stages[stage].mode); + + /* + * Record the original change status (or 'type' of change). If it + * was originally an add ('A'), this lets us differentiate later + * between a RENAME_DELETE conflict and RENAME_VIA_DIR (they + * otherwise look the same). If it was originally a rename ('R'), + * this lets us remember and report accurately about the transitive + * renaming that occurred via the directory rename detection. Also, + * record the original destination name. + */ + re->dir_rename_original_type = pair->status; + re->dir_rename_original_dest = pair->two->path; + + /* + * We don't actually look at pair->status again, but it seems + * pedagogically correct to adjust it. + */ + pair->status = 'R'; + + /* + * Finally, record the new location. + */ + pair->two->path = new_path; +} + +/* + * Get information of all renames which occurred in 'pairs', making use of + * any implicit directory renames inferred from the other side of history. + * We need the three trees in the merge ('o_tree', 'a_tree' and 'b_tree') + * to be able to associate the correct cache entries with the rename + * information; tree is always equal to either a_tree or b_tree. + */ +static struct string_list *get_renames(struct merge_options *opt, + const char *branch, + struct diff_queue_struct *pairs, + struct hashmap *dir_renames, + struct hashmap *dir_rename_exclusions, + struct tree *tree, + struct tree *o_tree, + struct tree *a_tree, + struct tree *b_tree, + struct string_list *entries, + int *clean_merge) +{ + int i; + struct hashmap collisions; + struct hashmap_iter iter; + struct collision_entry *e; + struct string_list *renames; + + compute_collisions(&collisions, dir_renames, pairs); + CALLOC_ARRAY(renames, 1); + + for (i = 0; i < pairs->nr; ++i) { + struct string_list_item *item; + struct rename *re; + struct diff_filepair *pair = pairs->queue[i]; + char *new_path; /* non-NULL only with directory renames */ + + if (pair->status != 'A' && pair->status != 'R') { + diff_free_filepair(pair); + continue; + } + new_path = check_for_directory_rename(opt, pair->two->path, tree, + dir_renames, + dir_rename_exclusions, + &collisions, + clean_merge); + if (pair->status != 'R' && !new_path) { + diff_free_filepair(pair); + continue; + } + + re = xmalloc(sizeof(*re)); + re->processed = 0; + re->pair = pair; + re->branch = branch; + re->dir_rename_original_type = '\0'; + re->dir_rename_original_dest = NULL; + item = string_list_lookup(entries, re->pair->one->path); + if (!item) + re->src_entry = insert_stage_data(opt->repo, + re->pair->one->path, + o_tree, a_tree, b_tree, entries); + else + re->src_entry = item->util; + + item = string_list_lookup(entries, re->pair->two->path); + if (!item) + re->dst_entry = insert_stage_data(opt->repo, + re->pair->two->path, + o_tree, a_tree, b_tree, entries); + else + re->dst_entry = item->util; + item = string_list_insert(renames, pair->one->path); + item->util = re; + if (new_path) + apply_directory_rename_modifications(opt, pair, new_path, + re, tree, o_tree, + a_tree, b_tree, + entries); + } + + hashmap_for_each_entry(&collisions, &iter, e, + ent /* member name */) { + free(e->target_file); + string_list_clear(&e->source_files, 0); + } + hashmap_clear_and_free(&collisions, struct collision_entry, ent); + return renames; +} + +static int process_renames(struct merge_options *opt, + struct string_list *a_renames, + struct string_list *b_renames) +{ + int clean_merge = 1, i, j; + struct string_list a_by_dst = STRING_LIST_INIT_NODUP; + struct string_list b_by_dst = STRING_LIST_INIT_NODUP; + const struct rename *sre; + + /* + * Note that as we build the list, we do not need to check if the + * existing destination path is already in the list, because the + * structure of diffcore_rename guarantees we won't have duplicates. + */ + for (i = 0; i < a_renames->nr; i++) { + sre = a_renames->items[i].util; + string_list_append(&a_by_dst, sre->pair->two->path)->util + = (void *)sre; + } + for (i = 0; i < b_renames->nr; i++) { + sre = b_renames->items[i].util; + string_list_append(&b_by_dst, sre->pair->two->path)->util + = (void *)sre; + } + string_list_sort(&a_by_dst); + string_list_sort(&b_by_dst); + + for (i = 0, j = 0; i < a_renames->nr || j < b_renames->nr;) { + struct string_list *renames1, *renames2Dst; + struct rename *ren1 = NULL, *ren2 = NULL; + const char *ren1_src, *ren1_dst; + struct string_list_item *lookup; + + if (i >= a_renames->nr) { + ren2 = b_renames->items[j++].util; + } else if (j >= b_renames->nr) { + ren1 = a_renames->items[i++].util; + } else { + int compare = strcmp(a_renames->items[i].string, + b_renames->items[j].string); + if (compare <= 0) + ren1 = a_renames->items[i++].util; + if (compare >= 0) + ren2 = b_renames->items[j++].util; + } + + /* TODO: refactor, so that 1/2 are not needed */ + if (ren1) { + renames1 = a_renames; + renames2Dst = &b_by_dst; + } else { + renames1 = b_renames; + renames2Dst = &a_by_dst; + SWAP(ren2, ren1); + } + + if (ren1->processed) + continue; + ren1->processed = 1; + ren1->dst_entry->processed = 1; + /* BUG: We should only mark src_entry as processed if we + * are not dealing with a rename + add-source case. + */ + ren1->src_entry->processed = 1; + + ren1_src = ren1->pair->one->path; + ren1_dst = ren1->pair->two->path; + + if (ren2) { + /* One file renamed on both sides */ + const char *ren2_src = ren2->pair->one->path; + const char *ren2_dst = ren2->pair->two->path; + enum rename_type rename_type; + if (strcmp(ren1_src, ren2_src) != 0) + BUG("ren1_src != ren2_src"); + ren2->dst_entry->processed = 1; + ren2->processed = 1; + if (strcmp(ren1_dst, ren2_dst) != 0) { + rename_type = RENAME_ONE_FILE_TO_TWO; + clean_merge = 0; + } else { + rename_type = RENAME_ONE_FILE_TO_ONE; + /* BUG: We should only remove ren1_src in + * the base stage (think of rename + + * add-source cases). + */ + remove_file(opt, 1, ren1_src, 1); + update_entry(ren1->dst_entry, + ren1->pair->one, + ren1->pair->two, + ren2->pair->two); + } + setup_rename_conflict_info(rename_type, opt, ren1, ren2); + } else if ((lookup = string_list_lookup(renames2Dst, ren1_dst))) { + /* Two different files renamed to the same thing */ + char *ren2_dst; + ren2 = lookup->util; + ren2_dst = ren2->pair->two->path; + if (strcmp(ren1_dst, ren2_dst) != 0) + BUG("ren1_dst != ren2_dst"); + + clean_merge = 0; + ren2->processed = 1; + /* + * BUG: We should only mark src_entry as processed + * if we are not dealing with a rename + add-source + * case. + */ + ren2->src_entry->processed = 1; + + setup_rename_conflict_info(RENAME_TWO_FILES_TO_ONE, + opt, ren1, ren2); + } else { + /* Renamed in 1, maybe changed in 2 */ + /* we only use sha1 and mode of these */ + struct diff_filespec src_other, dst_other; + int try_merge; + + /* + * unpack_trees loads entries from common-commit + * into stage 1, from head-commit into stage 2, and + * from merge-commit into stage 3. We keep track + * of which side corresponds to the rename. + */ + int renamed_stage = a_renames == renames1 ? 2 : 3; + int other_stage = a_renames == renames1 ? 3 : 2; + + /* + * Directory renames have a funny corner case... + */ + int renamed_to_self = !strcmp(ren1_src, ren1_dst); + + /* BUG: We should only remove ren1_src in the base + * stage and in other_stage (think of rename + + * add-source case). + */ + if (!renamed_to_self) + remove_file(opt, 1, ren1_src, + renamed_stage == 2 || + !was_tracked(opt, ren1_src)); + + oidcpy(&src_other.oid, + &ren1->src_entry->stages[other_stage].oid); + src_other.mode = ren1->src_entry->stages[other_stage].mode; + oidcpy(&dst_other.oid, + &ren1->dst_entry->stages[other_stage].oid); + dst_other.mode = ren1->dst_entry->stages[other_stage].mode; + try_merge = 0; + + if (oideq(&src_other.oid, null_oid(the_hash_algo)) && + ren1->dir_rename_original_type == 'A') { + setup_rename_conflict_info(RENAME_VIA_DIR, + opt, ren1, NULL); + } else if (renamed_to_self) { + setup_rename_conflict_info(RENAME_NORMAL, + opt, ren1, NULL); + } else if (oideq(&src_other.oid, null_oid(the_hash_algo))) { + setup_rename_conflict_info(RENAME_DELETE, + opt, ren1, NULL); + } else if ((dst_other.mode == ren1->pair->two->mode) && + oideq(&dst_other.oid, &ren1->pair->two->oid)) { + /* + * Added file on the other side identical to + * the file being renamed: clean merge. + * Also, there is no need to overwrite the + * file already in the working copy, so call + * update_file_flags() instead of + * update_file(). + */ + if (update_file_flags(opt, + ren1->pair->two, + ren1_dst, + 1, /* update_cache */ + 0 /* update_wd */)) + clean_merge = -1; + } else if (!oideq(&dst_other.oid, null_oid(the_hash_algo))) { + /* + * Probably not a clean merge, but it's + * premature to set clean_merge to 0 here, + * because if the rename merges cleanly and + * the merge exactly matches the newly added + * file, then the merge will be clean. + */ + setup_rename_conflict_info(RENAME_ADD, + opt, ren1, NULL); + } else + try_merge = 1; + + if (clean_merge < 0) + goto cleanup_and_return; + if (try_merge) { + struct diff_filespec *o, *a, *b; + src_other.path = (char *)ren1_src; + + o = ren1->pair->one; + if (a_renames == renames1) { + a = ren1->pair->two; + b = &src_other; + } else { + b = ren1->pair->two; + a = &src_other; + } + update_entry(ren1->dst_entry, o, a, b); + setup_rename_conflict_info(RENAME_NORMAL, + opt, ren1, NULL); + } + } + } +cleanup_and_return: + string_list_clear(&a_by_dst, 0); + string_list_clear(&b_by_dst, 0); + + return clean_merge; +} + +struct rename_info { + struct string_list *head_renames; + struct string_list *merge_renames; +}; + +static void initial_cleanup_rename(struct diff_queue_struct *pairs, + struct hashmap *dir_renames) +{ + struct hashmap_iter iter; + struct dir_rename_entry *e; + + hashmap_for_each_entry(dir_renames, &iter, e, + ent /* member name */) { + free(e->dir); + strbuf_release(&e->new_dir); + /* possible_new_dirs already cleared in get_directory_renames */ + } + hashmap_clear_and_free(dir_renames, struct dir_rename_entry, ent); + free(dir_renames); + + free(pairs->queue); + free(pairs); +} + +static int detect_and_process_renames(struct merge_options *opt, + struct tree *common, + struct tree *head, + struct tree *merge, + struct string_list *entries, + struct rename_info *ri) +{ + struct diff_queue_struct *head_pairs, *merge_pairs; + struct hashmap *dir_re_head, *dir_re_merge; + int clean = 1; + + ri->head_renames = NULL; + ri->merge_renames = NULL; + + if (!merge_detect_rename(opt)) + return 1; + + head_pairs = get_diffpairs(opt, common, head); + merge_pairs = get_diffpairs(opt, common, merge); + + if ((opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_TRUE) || + (opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_CONFLICT && + !opt->priv->call_depth)) { + dir_re_head = get_directory_renames(head_pairs); + dir_re_merge = get_directory_renames(merge_pairs); + + handle_directory_level_conflicts(opt, + dir_re_head, head, + dir_re_merge, merge); + } else { + dir_re_head = xmalloc(sizeof(*dir_re_head)); + dir_re_merge = xmalloc(sizeof(*dir_re_merge)); + dir_rename_init(dir_re_head); + dir_rename_init(dir_re_merge); + } + + ri->head_renames = get_renames(opt, opt->branch1, head_pairs, + dir_re_merge, dir_re_head, head, + common, head, merge, entries, + &clean); + if (clean < 0) + goto cleanup; + ri->merge_renames = get_renames(opt, opt->branch2, merge_pairs, + dir_re_head, dir_re_merge, merge, + common, head, merge, entries, + &clean); + if (clean < 0) + goto cleanup; + clean &= process_renames(opt, ri->head_renames, ri->merge_renames); + +cleanup: + /* + * Some cleanup is deferred until cleanup_renames() because the + * data structures are still needed and referenced in + * process_entry(). But there are a few things we can free now. + */ + initial_cleanup_rename(head_pairs, dir_re_head); + initial_cleanup_rename(merge_pairs, dir_re_merge); + + return clean; +} + +static void final_cleanup_rename(struct string_list *rename) +{ + const struct rename *re; + int i; + + if (!rename) + return; + + for (i = 0; i < rename->nr; i++) { + re = rename->items[i].util; + diff_free_filepair(re->pair); + if (re->src_entry->rename_conflict_info_owned) + FREE_AND_NULL(re->src_entry->rename_conflict_info); + if (re->dst_entry->rename_conflict_info_owned) + FREE_AND_NULL(re->dst_entry->rename_conflict_info); + } + string_list_clear(rename, 1); + free(rename); +} + +static void final_cleanup_renames(struct rename_info *re_info) +{ + final_cleanup_rename(re_info->head_renames); + final_cleanup_rename(re_info->merge_renames); +} + +static int read_oid_strbuf(struct merge_options *opt, + const struct object_id *oid, + struct strbuf *dst) +{ + void *buf; + enum object_type type; + unsigned long size; + buf = repo_read_object_file(the_repository, oid, &type, &size); + if (!buf) + return err(opt, _("cannot read object %s"), oid_to_hex(oid)); + if (type != OBJ_BLOB) { + free(buf); + return err(opt, _("object %s is not a blob"), oid_to_hex(oid)); + } + strbuf_attach(dst, buf, size, size + 1); + return 0; +} + +static int blob_unchanged(struct merge_options *opt, + const struct diff_filespec *o, + const struct diff_filespec *a, + int renormalize, const char *path) +{ + struct strbuf obuf = STRBUF_INIT; + struct strbuf abuf = STRBUF_INIT; + int ret = 0; /* assume changed for safety */ + struct index_state *idx = opt->repo->index; + + if (a->mode != o->mode) + return 0; + if (oideq(&o->oid, &a->oid)) + return 1; + if (!renormalize) + return 0; + + if (read_oid_strbuf(opt, &o->oid, &obuf) || + read_oid_strbuf(opt, &a->oid, &abuf)) + goto error_return; + /* + * Note: binary | is used so that both renormalizations are + * performed. Comparison can be skipped if both files are + * unchanged since their sha1s have already been compared. + */ + if (renormalize_buffer(idx, path, obuf.buf, obuf.len, &obuf) | + renormalize_buffer(idx, path, abuf.buf, abuf.len, &abuf)) + ret = (obuf.len == abuf.len && !memcmp(obuf.buf, abuf.buf, obuf.len)); + +error_return: + strbuf_release(&obuf); + strbuf_release(&abuf); + return ret; +} + +static int handle_modify_delete(struct merge_options *opt, + const char *path, + const struct diff_filespec *o, + const struct diff_filespec *a, + const struct diff_filespec *b) +{ + const char *modify_branch, *delete_branch; + const struct diff_filespec *changed; + + if (is_valid(a)) { + modify_branch = opt->branch1; + delete_branch = opt->branch2; + changed = a; + } else { + modify_branch = opt->branch2; + delete_branch = opt->branch1; + changed = b; + } + + return handle_change_delete(opt, + path, NULL, + o, changed, + modify_branch, delete_branch, + _("modify"), _("modified")); +} + +static int handle_content_merge(struct merge_file_info *mfi, + struct merge_options *opt, + const char *path, + int is_dirty, + const struct diff_filespec *o, + const struct diff_filespec *a, + const struct diff_filespec *b, + struct rename_conflict_info *ci) +{ + const char *reason = _("content"); + unsigned df_conflict_remains = 0; + + if (!is_valid(o)) + reason = _("add/add"); + + assert(o->path && a->path && b->path); + if (ci && dir_in_way(opt->repo->index, path, !opt->priv->call_depth, + S_ISGITLINK(ci->ren1->pair->two->mode))) + df_conflict_remains = 1; + + if (merge_mode_and_contents(opt, o, a, b, path, + opt->branch1, opt->branch2, + opt->priv->call_depth * 2, mfi)) + return -1; + + /* + * We can skip updating the working tree file iff: + * a) The merge is clean + * b) The merge matches what was in HEAD (content, mode, pathname) + * c) The target path is usable (i.e. not involved in D/F conflict) + */ + if (mfi->clean && was_tracked_and_matches(opt, path, &mfi->blob) && + !df_conflict_remains) { + int pos; + struct cache_entry *ce; + + output(opt, 3, _("Skipped %s (merged same as existing)"), path); + if (add_cacheinfo(opt, &mfi->blob, path, + 0, (!opt->priv->call_depth && !is_dirty), 0)) + return -1; + /* + * However, add_cacheinfo() will delete the old cache entry + * and add a new one. We need to copy over any skip_worktree + * flag to avoid making the file appear as if it were + * deleted by the user. + */ + pos = index_name_pos(&opt->priv->orig_index, path, strlen(path)); + ce = opt->priv->orig_index.cache[pos]; + if (ce_skip_worktree(ce)) { + pos = index_name_pos(opt->repo->index, path, strlen(path)); + ce = opt->repo->index->cache[pos]; + ce->ce_flags |= CE_SKIP_WORKTREE; + } + return mfi->clean; + } + + if (!mfi->clean) { + if (S_ISGITLINK(mfi->blob.mode)) + reason = _("submodule"); + output(opt, 1, _("CONFLICT (%s): Merge conflict in %s"), + reason, path); + if (ci && !df_conflict_remains) + if (update_stages(opt, path, o, a, b)) + return -1; + } + + if (df_conflict_remains || is_dirty) { + char *new_path; + if (opt->priv->call_depth) { + remove_file_from_index(opt->repo->index, path); + } else { + if (!mfi->clean) { + if (update_stages(opt, path, o, a, b)) + return -1; + } else { + int file_from_stage2 = was_tracked(opt, path); + + if (update_stages(opt, path, NULL, + file_from_stage2 ? &mfi->blob : NULL, + file_from_stage2 ? NULL : &mfi->blob)) + return -1; + } + + } + new_path = unique_path(opt, path, ci->ren1->branch); + if (is_dirty) { + output(opt, 1, _("Refusing to lose dirty file at %s"), + path); + } + output(opt, 1, _("Adding as %s instead"), new_path); + if (update_file(opt, 0, &mfi->blob, new_path)) { + free(new_path); + return -1; + } + free(new_path); + mfi->clean = 0; + } else if (update_file(opt, mfi->clean, &mfi->blob, path)) + return -1; + return !is_dirty && mfi->clean; +} + +static int handle_rename_normal(struct merge_options *opt, + const char *path, + const struct diff_filespec *o, + const struct diff_filespec *a, + const struct diff_filespec *b, + struct rename_conflict_info *ci) +{ + struct rename *ren = ci->ren1; + struct merge_file_info mfi; + int clean; + + /* Merge the content and write it out */ + clean = handle_content_merge(&mfi, opt, path, was_dirty(opt, path), + o, a, b, ci); + + if (clean && + opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_CONFLICT && + ren->dir_rename_original_dest) { + if (update_stages(opt, path, + &mfi.blob, &mfi.blob, &mfi.blob)) + return -1; + clean = 0; /* not clean, but conflicted */ + } + return clean; +} + +static void dir_rename_warning(const char *msg, + int is_add, + int clean, + struct merge_options *opt, + struct rename *ren) +{ + const char *other_branch; + other_branch = (ren->branch == opt->branch1 ? + opt->branch2 : opt->branch1); + if (is_add) { + output(opt, clean ? 2 : 1, msg, + ren->pair->one->path, ren->branch, + other_branch, ren->pair->two->path); + return; + } + output(opt, clean ? 2 : 1, msg, + ren->pair->one->path, ren->dir_rename_original_dest, ren->branch, + other_branch, ren->pair->two->path); +} +static int warn_about_dir_renamed_entries(struct merge_options *opt, + struct rename *ren) +{ + const char *msg; + int clean = 1, is_add; + + if (!ren) + return clean; + + /* Return early if ren was not affected/created by a directory rename */ + if (!ren->dir_rename_original_dest) + return clean; + + /* Sanity checks */ + assert(opt->detect_directory_renames > MERGE_DIRECTORY_RENAMES_NONE); + assert(ren->dir_rename_original_type == 'A' || + ren->dir_rename_original_type == 'R'); + + /* Check whether to treat directory renames as a conflict */ + clean = (opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_TRUE); + + is_add = (ren->dir_rename_original_type == 'A'); + if (ren->dir_rename_original_type == 'A' && clean) { + msg = _("Path updated: %s added in %s inside a " + "directory that was renamed in %s; moving it to %s."); + } else if (ren->dir_rename_original_type == 'A' && !clean) { + msg = _("CONFLICT (file location): %s added in %s " + "inside a directory that was renamed in %s, " + "suggesting it should perhaps be moved to %s."); + } else if (ren->dir_rename_original_type == 'R' && clean) { + msg = _("Path updated: %s renamed to %s in %s, inside a " + "directory that was renamed in %s; moving it to %s."); + } else if (ren->dir_rename_original_type == 'R' && !clean) { + msg = _("CONFLICT (file location): %s renamed to %s in %s, " + "inside a directory that was renamed in %s, " + "suggesting it should perhaps be moved to %s."); + } else { + BUG("Impossible dir_rename_original_type/clean combination"); + } + dir_rename_warning(msg, is_add, clean, opt, ren); + + return clean; +} + +/* Per entry merge function */ +static int process_entry(struct merge_options *opt, + const char *path, struct stage_data *entry) +{ + int clean_merge = 1; + int normalize = opt->renormalize; + + struct diff_filespec *o = &entry->stages[1]; + struct diff_filespec *a = &entry->stages[2]; + struct diff_filespec *b = &entry->stages[3]; + int o_valid = is_valid(o); + int a_valid = is_valid(a); + int b_valid = is_valid(b); + o->path = a->path = b->path = (char*)path; + + entry->processed = 1; + if (entry->rename_conflict_info) { + struct rename_conflict_info *ci = entry->rename_conflict_info; + struct diff_filespec *temp; + int path_clean; + + path_clean = warn_about_dir_renamed_entries(opt, ci->ren1); + path_clean &= warn_about_dir_renamed_entries(opt, ci->ren2); + + /* + * For cases with a single rename, {o,a,b}->path have all been + * set to the rename target path; we need to set two of these + * back to the rename source. + * For rename/rename conflicts, we'll manually fix paths below. + */ + temp = (opt->branch1 == ci->ren1->branch) ? b : a; + o->path = temp->path = ci->ren1->pair->one->path; + if (ci->ren2) { + assert(opt->branch1 == ci->ren1->branch); + } + + switch (ci->rename_type) { + case RENAME_NORMAL: + case RENAME_ONE_FILE_TO_ONE: + clean_merge = handle_rename_normal(opt, path, o, a, b, + ci); + break; + case RENAME_VIA_DIR: + clean_merge = handle_rename_via_dir(opt, ci); + break; + case RENAME_ADD: + /* + * Probably unclean merge, but if the renamed file + * merges cleanly and the result can then be + * two-way merged cleanly with the added file, I + * guess it's a clean merge? + */ + clean_merge = handle_rename_add(opt, ci); + break; + case RENAME_DELETE: + clean_merge = 0; + if (handle_rename_delete(opt, ci)) + clean_merge = -1; + break; + case RENAME_ONE_FILE_TO_TWO: + /* + * Manually fix up paths; note: + * ren[12]->pair->one->path are equal. + */ + o->path = ci->ren1->pair->one->path; + a->path = ci->ren1->pair->two->path; + b->path = ci->ren2->pair->two->path; + + clean_merge = 0; + if (handle_rename_rename_1to2(opt, ci)) + clean_merge = -1; + break; + case RENAME_TWO_FILES_TO_ONE: + /* + * Manually fix up paths; note, + * ren[12]->pair->two->path are actually equal. + */ + o->path = NULL; + a->path = ci->ren1->pair->two->path; + b->path = ci->ren2->pair->two->path; + + /* + * Probably unclean merge, but if the two renamed + * files merge cleanly and the two resulting files + * can then be two-way merged cleanly, I guess it's + * a clean merge? + */ + clean_merge = handle_rename_rename_2to1(opt, ci); + break; + default: + entry->processed = 0; + break; + } + if (path_clean < clean_merge) + clean_merge = path_clean; + } else if (o_valid && (!a_valid || !b_valid)) { + /* Case A: Deleted in one */ + if ((!a_valid && !b_valid) || + (!b_valid && blob_unchanged(opt, o, a, normalize, path)) || + (!a_valid && blob_unchanged(opt, o, b, normalize, path))) { + /* Deleted in both or deleted in one and + * unchanged in the other */ + if (a_valid) + output(opt, 2, _("Removing %s"), path); + /* do not touch working file if it did not exist */ + remove_file(opt, 1, path, !a_valid); + } else { + /* Modify/delete; deleted side may have put a directory in the way */ + clean_merge = 0; + if (handle_modify_delete(opt, path, o, a, b)) + clean_merge = -1; + } + } else if ((!o_valid && a_valid && !b_valid) || + (!o_valid && !a_valid && b_valid)) { + /* Case B: Added in one. */ + /* [nothing|directory] -> ([nothing|directory], file) */ + + const char *add_branch; + const char *other_branch; + const char *conf; + const struct diff_filespec *contents; + + if (a_valid) { + add_branch = opt->branch1; + other_branch = opt->branch2; + contents = a; + conf = _("file/directory"); + } else { + add_branch = opt->branch2; + other_branch = opt->branch1; + contents = b; + conf = _("directory/file"); + } + if (dir_in_way(opt->repo->index, path, + !opt->priv->call_depth && !S_ISGITLINK(a->mode), + 0)) { + char *new_path = unique_path(opt, path, add_branch); + clean_merge = 0; + output(opt, 1, _("CONFLICT (%s): There is a directory with name %s in %s. " + "Adding %s as %s"), + conf, path, other_branch, path, new_path); + if (update_file(opt, 0, contents, new_path)) + clean_merge = -1; + else if (opt->priv->call_depth) + remove_file_from_index(opt->repo->index, path); + free(new_path); + } else { + output(opt, 2, _("Adding %s"), path); + /* do not overwrite file if already present */ + if (update_file_flags(opt, contents, path, 1, !a_valid)) + clean_merge = -1; + } + } else if (a_valid && b_valid) { + if (!o_valid) { + /* Case C: Added in both (check for same permissions) */ + output(opt, 1, + _("CONFLICT (add/add): Merge conflict in %s"), + path); + clean_merge = handle_file_collision(opt, + path, NULL, NULL, + opt->branch1, + opt->branch2, + a, b); + } else { + /* case D: Modified in both, but differently. */ + struct merge_file_info mfi; + int is_dirty = 0; /* unpack_trees would have bailed if dirty */ + clean_merge = handle_content_merge(&mfi, opt, path, + is_dirty, + o, a, b, NULL); + } + } else if (!o_valid && !a_valid && !b_valid) { + /* + * this entry was deleted altogether. a_mode == 0 means + * we had that path and want to actively remove it. + */ + remove_file(opt, 1, path, !a->mode); + } else + BUG("fatal merge failure, shouldn't happen."); + + return clean_merge; +} + +static int merge_trees_internal(struct merge_options *opt, + struct tree *head, + struct tree *merge, + struct tree *merge_base, + struct tree **result) +{ + struct index_state *istate = opt->repo->index; + int code, clean; + + if (opt->subtree_shift) { + merge = shift_tree_object(opt->repo, head, merge, + opt->subtree_shift); + merge_base = shift_tree_object(opt->repo, head, merge_base, + opt->subtree_shift); + } + + if (oideq(&merge_base->object.oid, &merge->object.oid)) { + output(opt, 0, _("Already up to date.")); + *result = head; + return 1; + } + + code = unpack_trees_start(opt, merge_base, head, merge); + + if (code != 0) { + if (show(opt, 4) || opt->priv->call_depth) + err(opt, _("merging of trees %s and %s failed"), + oid_to_hex(&head->object.oid), + oid_to_hex(&merge->object.oid)); + unpack_trees_finish(opt); + return -1; + } + + if (unmerged_index(istate)) { + struct string_list *entries; + struct rename_info re_info; + int i; + /* + * Only need the hashmap while processing entries, so + * initialize it here and free it when we are done running + * through the entries. Keeping it in the merge_options as + * opposed to decaring a local hashmap is for convenience + * so that we don't have to pass it to around. + */ + hashmap_init(&opt->priv->current_file_dir_set, path_hashmap_cmp, + NULL, 512); + get_files_dirs(opt, head); + get_files_dirs(opt, merge); + + entries = get_unmerged(opt->repo->index); + clean = detect_and_process_renames(opt, merge_base, head, merge, + entries, &re_info); + record_df_conflict_files(opt, entries); + if (clean < 0) + goto cleanup; + for (i = entries->nr-1; 0 <= i; i--) { + const char *path = entries->items[i].string; + struct stage_data *e = entries->items[i].util; + if (!e->processed) { + int ret = process_entry(opt, path, e); + if (!ret) + clean = 0; + else if (ret < 0) { + clean = ret; + goto cleanup; + } + } + } + for (i = 0; i < entries->nr; i++) { + struct stage_data *e = entries->items[i].util; + if (!e->processed) + BUG("unprocessed path??? %s", + entries->items[i].string); + } + + cleanup: + final_cleanup_renames(&re_info); + + string_list_clear(entries, 1); + free(entries); + + hashmap_clear_and_free(&opt->priv->current_file_dir_set, + struct path_hashmap_entry, e); + + if (clean < 0) { + unpack_trees_finish(opt); + return clean; + } + } + else + clean = 1; + + unpack_trees_finish(opt); + + if (opt->priv->call_depth && + !(*result = write_in_core_index_as_tree(opt->repo))) + return -1; + + return clean; +} + +/* + * Merge the commits h1 and h2, returning a flag (int) indicating the + * cleanness of the merge. Also, if opt->priv->call_depth, create a + * virtual commit and write its location to *result. + */ +static int merge_recursive_internal(struct merge_options *opt, + struct commit *h1, + struct commit *h2, + const struct commit_list *_merge_bases, + struct commit **result) +{ + struct commit_list *merge_bases = copy_commit_list(_merge_bases); + struct commit_list *iter; + struct commit *merged_merge_bases; + struct tree *result_tree; + const char *ancestor_name; + struct strbuf merge_base_abbrev = STRBUF_INIT; + int ret; + + if (show(opt, 4)) { + output(opt, 4, _("Merging:")); + output_commit_title(opt, h1); + output_commit_title(opt, h2); + } + + if (!merge_bases) { + if (repo_get_merge_bases(the_repository, h1, h2, + &merge_bases) < 0) { + ret = -1; + goto out; + } + merge_bases = reverse_commit_list(merge_bases); + } + + if (show(opt, 5)) { + unsigned cnt = commit_list_count(merge_bases); + + output(opt, 5, Q_("found %u common ancestor:", + "found %u common ancestors:", cnt), cnt); + for (iter = merge_bases; iter; iter = iter->next) + output_commit_title(opt, iter->item); + } + + merged_merge_bases = pop_commit(&merge_bases); + if (!merged_merge_bases) { + /* if there is no common ancestor, use an empty tree */ + struct tree *tree; + + tree = lookup_tree(opt->repo, opt->repo->hash_algo->empty_tree); + merged_merge_bases = make_virtual_commit(opt->repo, tree, + "ancestor"); + ancestor_name = "empty tree"; + } else if (opt->ancestor && !opt->priv->call_depth) { + ancestor_name = opt->ancestor; + } else if (merge_bases) { + ancestor_name = "merged common ancestors"; + } else { + strbuf_add_unique_abbrev(&merge_base_abbrev, + &merged_merge_bases->object.oid, + DEFAULT_ABBREV); + ancestor_name = merge_base_abbrev.buf; + } + + for (iter = merge_bases; iter; iter = iter->next) { + const char *saved_b1, *saved_b2; + opt->priv->call_depth++; + /* + * When the merge fails, the result contains files + * with conflict markers. The cleanness flag is + * ignored (unless indicating an error), it was never + * actually used, as result of merge_trees has always + * overwritten it: the committed "conflicts" were + * already resolved. + */ + discard_index(opt->repo->index); + saved_b1 = opt->branch1; + saved_b2 = opt->branch2; + opt->branch1 = "Temporary merge branch 1"; + opt->branch2 = "Temporary merge branch 2"; + if (merge_recursive_internal(opt, merged_merge_bases, iter->item, + NULL, &merged_merge_bases) < 0) { + ret = -1; + goto out; + } + opt->branch1 = saved_b1; + opt->branch2 = saved_b2; + opt->priv->call_depth--; + + if (!merged_merge_bases) { + ret = err(opt, _("merge returned no commit")); + goto out; + } + } + + /* + * FIXME: Since merge_recursive_internal() is only ever called by + * places that ensure the index is loaded first + * (e.g. builtin/merge.c, rebase/sequencer, etc.), in the common + * case where the merge base was unique that means when we get here + * we immediately discard the index and re-read it, which is a + * complete waste of time. We should only be discarding and + * re-reading if we were forced to recurse. + */ + discard_index(opt->repo->index); + if (!opt->priv->call_depth) + repo_read_index(opt->repo); + + opt->ancestor = ancestor_name; + ret = merge_trees_internal(opt, + repo_get_commit_tree(opt->repo, h1), + repo_get_commit_tree(opt->repo, h2), + repo_get_commit_tree(opt->repo, + merged_merge_bases), + &result_tree); + opt->ancestor = NULL; /* avoid accidental re-use of opt->ancestor */ + if (ret < 0) { + flush_output(opt); + goto out; + } + + if (opt->priv->call_depth) { + *result = make_virtual_commit(opt->repo, result_tree, + "merged tree"); + commit_list_insert(h1, &(*result)->parents); + commit_list_insert(h2, &(*result)->parents->next); + } + +out: + strbuf_release(&merge_base_abbrev); + free_commit_list(merge_bases); + return ret; +} + +static int merge_start(struct merge_options *opt, struct tree *head) +{ + struct strbuf sb = STRBUF_INIT; + + /* Sanity checks on opt */ + assert(opt->repo); + + assert(opt->branch1 && opt->branch2); + + assert(opt->detect_renames >= -1 && + opt->detect_renames <= DIFF_DETECT_COPY); + assert(opt->detect_directory_renames >= MERGE_DIRECTORY_RENAMES_NONE && + opt->detect_directory_renames <= MERGE_DIRECTORY_RENAMES_TRUE); + assert(opt->rename_limit >= -1); + assert(opt->rename_score >= 0 && opt->rename_score <= MAX_SCORE); + assert(opt->show_rename_progress >= 0 && opt->show_rename_progress <= 1); + + assert(opt->xdl_opts >= 0); + assert(opt->recursive_variant >= MERGE_VARIANT_NORMAL && + opt->recursive_variant <= MERGE_VARIANT_THEIRS); + + assert(opt->verbosity >= 0 && opt->verbosity <= 5); + assert(opt->buffer_output <= 2); + assert(opt->obuf.len == 0); + + assert(opt->priv == NULL); + + /* Not supported; option specific to merge-ort */ + assert(!opt->record_conflict_msgs_as_headers); + assert(!opt->msg_header_prefix); + + /* Sanity check on repo state; index must match head */ + if (repo_index_has_changes(opt->repo, head, &sb)) { + err(opt, _("Your local changes to the following files would be overwritten by merge:\n %s"), + sb.buf); + strbuf_release(&sb); + return -1; + } + + CALLOC_ARRAY(opt->priv, 1); + string_list_init_dup(&opt->priv->df_conflict_file_set); + return 0; +} + +static void merge_finalize(struct merge_options *opt) +{ + flush_output(opt); + if (!opt->priv->call_depth && opt->buffer_output < 2) + strbuf_release(&opt->obuf); + if (show(opt, 2)) + diff_warn_rename_limit("merge.renamelimit", + opt->priv->needed_rename_limit, 0); + hashmap_clear_and_free(&opt->priv->current_file_dir_set, + struct path_hashmap_entry, e); + string_list_clear(&opt->priv->df_conflict_file_set, 0); + FREE_AND_NULL(opt->priv); +} + +int merge_trees(struct merge_options *opt, + struct tree *head, + struct tree *merge, + struct tree *merge_base) +{ + int clean; + struct tree *ignored; + + assert(opt->ancestor != NULL); + + if (merge_start(opt, head)) + return -1; + clean = merge_trees_internal(opt, head, merge, merge_base, &ignored); + merge_finalize(opt); + + return clean; +} + +int merge_recursive(struct merge_options *opt, + struct commit *h1, + struct commit *h2, + const struct commit_list *merge_bases, + struct commit **result) +{ + int clean; + + assert(opt->ancestor == NULL || + !strcmp(opt->ancestor, "constructed merge base")); + + prepare_repo_settings(opt->repo); + opt->repo->settings.command_requires_full_index = 1; + + if (merge_start(opt, repo_get_commit_tree(opt->repo, h1))) + return -1; + clean = merge_recursive_internal(opt, h1, h2, merge_bases, result); + merge_finalize(opt); + + return clean; +} + +static struct commit *get_ref(struct repository *repo, + const struct object_id *oid, + const char *name) +{ + struct object *object; + + object = deref_tag(repo, parse_object(repo, oid), + name, strlen(name)); + if (!object) + return NULL; + if (object->type == OBJ_TREE) + return make_virtual_commit(repo, (struct tree*)object, name); + if (object->type != OBJ_COMMIT) + return NULL; + if (repo_parse_commit(repo, (struct commit *)object)) + return NULL; + return (struct commit *)object; +} + +int merge_recursive_generic(struct merge_options *opt, + const struct object_id *head, + const struct object_id *merge, + int num_merge_bases, + const struct object_id *merge_bases, + struct commit **result) +{ + int clean; + struct lock_file lock = LOCK_INIT; + struct commit *head_commit = get_ref(opt->repo, head, opt->branch1); + struct commit *next_commit = get_ref(opt->repo, merge, opt->branch2); + struct commit_list *ca = NULL; + + if (merge_bases) { + int i; + for (i = 0; i < num_merge_bases; ++i) { + struct commit *base; + if (!(base = get_ref(opt->repo, &merge_bases[i], + oid_to_hex(&merge_bases[i])))) + return err(opt, _("Could not parse object '%s'"), + oid_to_hex(&merge_bases[i])); + commit_list_insert(base, &ca); + } + if (num_merge_bases == 1) + opt->ancestor = "constructed merge base"; + } + + repo_hold_locked_index(opt->repo, &lock, LOCK_DIE_ON_ERROR); + clean = merge_recursive(opt, head_commit, next_commit, ca, + result); + free_commit_list(ca); + if (clean < 0) { + rollback_lock_file(&lock); + return clean; + } + + if (write_locked_index(opt->repo->index, &lock, + COMMIT_LOCK | SKIP_IF_UNCHANGED)) + return err(opt, _("Unable to write index.")); + + return clean ? 0 : 1; +} + +static void merge_recursive_config(struct merge_options *opt, int ui) +{ + char *value = NULL; + int renormalize = 0; + git_config_get_int("merge.verbosity", &opt->verbosity); + git_config_get_int("diff.renamelimit", &opt->rename_limit); + git_config_get_int("merge.renamelimit", &opt->rename_limit); + git_config_get_bool("merge.renormalize", &renormalize); + opt->renormalize = renormalize; + if (!git_config_get_string("diff.renames", &value)) { + opt->detect_renames = git_config_rename("diff.renames", value); + free(value); + } + if (!git_config_get_string("merge.renames", &value)) { + opt->detect_renames = git_config_rename("merge.renames", value); + free(value); + } + if (!git_config_get_string("merge.directoryrenames", &value)) { + int boolval = git_parse_maybe_bool(value); + if (0 <= boolval) { + opt->detect_directory_renames = boolval ? + MERGE_DIRECTORY_RENAMES_TRUE : + MERGE_DIRECTORY_RENAMES_NONE; + } else if (!strcasecmp(value, "conflict")) { + opt->detect_directory_renames = + MERGE_DIRECTORY_RENAMES_CONFLICT; + } /* avoid erroring on values from future versions of git */ + free(value); + } + if (ui) { + if (!git_config_get_string("diff.algorithm", &value)) { + long diff_algorithm = parse_algorithm_value(value); + if (diff_algorithm < 0) + die(_("unknown value for config '%s': %s"), "diff.algorithm", value); + opt->xdl_opts = (opt->xdl_opts & ~XDF_DIFF_ALGORITHM_MASK) | diff_algorithm; + free(value); + } + } + git_config(git_xmerge_config, NULL); +} + +static void init_merge_options(struct merge_options *opt, + struct repository *repo, int ui) +{ + const char *merge_verbosity; + memset(opt, 0, sizeof(struct merge_options)); + + opt->repo = repo; + + opt->detect_renames = -1; + opt->detect_directory_renames = MERGE_DIRECTORY_RENAMES_CONFLICT; + opt->rename_limit = -1; + + opt->verbosity = 2; + opt->buffer_output = 1; + strbuf_init(&opt->obuf, 0); + + opt->renormalize = 0; + + opt->conflict_style = -1; + + merge_recursive_config(opt, ui); + merge_verbosity = getenv("GIT_MERGE_VERBOSITY"); + if (merge_verbosity) + opt->verbosity = strtol(merge_verbosity, NULL, 10); + if (opt->verbosity >= 5) + opt->buffer_output = 0; +} + +void init_ui_merge_options(struct merge_options *opt, + struct repository *repo) +{ + init_merge_options(opt, repo, 1); +} + +void init_basic_merge_options(struct merge_options *opt, + struct repository *repo) +{ + init_merge_options(opt, repo, 0); +} + +/* + * For now, members of merge_options do not need deep copying, but + * it may change in the future, in which case we would need to update + * this, and also make a matching change to clear_merge_options() to + * release the resources held by a copied instance. + */ +void copy_merge_options(struct merge_options *dst, struct merge_options *src) +{ + *dst = *src; +} + +void clear_merge_options(struct merge_options *opt UNUSED) +{ + ; /* no-op as our copy is shallow right now */ +} + +int parse_merge_opt(struct merge_options *opt, const char *s) +{ + const char *arg; + + if (!s || !*s) + return -1; + if (!strcmp(s, "ours")) + opt->recursive_variant = MERGE_VARIANT_OURS; + else if (!strcmp(s, "theirs")) + opt->recursive_variant = MERGE_VARIANT_THEIRS; + else if (!strcmp(s, "subtree")) + opt->subtree_shift = ""; + else if (skip_prefix(s, "subtree=", &arg)) + opt->subtree_shift = arg; + else if (!strcmp(s, "patience")) + opt->xdl_opts = DIFF_WITH_ALG(opt, PATIENCE_DIFF); + else if (!strcmp(s, "histogram")) + opt->xdl_opts = DIFF_WITH_ALG(opt, HISTOGRAM_DIFF); + else if (skip_prefix(s, "diff-algorithm=", &arg)) { + long value = parse_algorithm_value(arg); + if (value < 0) + return -1; + /* clear out previous settings */ + DIFF_XDL_CLR(opt, NEED_MINIMAL); + opt->xdl_opts &= ~XDF_DIFF_ALGORITHM_MASK; + opt->xdl_opts |= value; + } + else if (!strcmp(s, "ignore-space-change")) + DIFF_XDL_SET(opt, IGNORE_WHITESPACE_CHANGE); + else if (!strcmp(s, "ignore-all-space")) + DIFF_XDL_SET(opt, IGNORE_WHITESPACE); + else if (!strcmp(s, "ignore-space-at-eol")) + DIFF_XDL_SET(opt, IGNORE_WHITESPACE_AT_EOL); + else if (!strcmp(s, "ignore-cr-at-eol")) + DIFF_XDL_SET(opt, IGNORE_CR_AT_EOL); + else if (!strcmp(s, "renormalize")) + opt->renormalize = 1; + else if (!strcmp(s, "no-renormalize")) + opt->renormalize = 0; + else if (!strcmp(s, "no-renames")) + opt->detect_renames = 0; + else if (!strcmp(s, "find-renames")) { + opt->detect_renames = 1; + opt->rename_score = 0; + } + else if (skip_prefix(s, "find-renames=", &arg) || + skip_prefix(s, "rename-threshold=", &arg)) { + if ((opt->rename_score = parse_rename_score(&arg)) == -1 || *arg != 0) + return -1; + opt->detect_renames = 1; + } + /* + * Please update $__git_merge_strategy_options in + * git-completion.bash when you add new options + */ + else + return -1; + return 0; +} 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); @@ -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", @@ -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 "<type> <obj-len>" 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 "<type> <obj-len>" 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 */ @@ -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) { @@ -567,70 +564,6 @@ 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" @@ -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; @@ -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 2f9e21c897..570744bb56 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" @@ -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" @@ -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); @@ -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" @@ -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 3fb4c4adb7..e8f89d16ae 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; @@ -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" @@ -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" @@ -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" @@ -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" @@ -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" |