diff options
Diffstat (limited to 'builtin/fsck.c')
-rw-r--r-- | builtin/fsck.c | 456 |
1 files changed, 316 insertions, 140 deletions
diff --git a/builtin/fsck.c b/builtin/fsck.c index 3f27456..06eb421 100644 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@ -1,5 +1,7 @@ #include "builtin.h" #include "cache.h" +#include "repository.h" +#include "config.h" #include "commit.h" #include "tree.h" #include "blob.h" @@ -13,10 +15,16 @@ #include "dir.h" #include "progress.h" #include "streaming.h" +#include "decorate.h" +#include "packfile.h" +#include "object-store.h" +#include "run-command.h" #define REACHABLE 0x0001 #define SEEN 0x0002 #define HAS_OBJ 0x0004 +/* This flag is set if something points to this object. */ +#define USED 0x0008 static int show_root; static int show_tags; @@ -35,10 +43,44 @@ static int write_lost_and_found; static int verbose; static int show_progress = -1; static int show_dangling = 1; +static int name_objects; #define ERROR_OBJECT 01 #define ERROR_REACHABLE 02 #define ERROR_PACK 04 #define ERROR_REFS 010 +#define ERROR_COMMIT_GRAPH 020 + +static const char *describe_object(struct object *obj) +{ + static struct strbuf buf = STRBUF_INIT; + char *name = name_objects ? + lookup_decoration(fsck_walk_options.object_names, obj) : NULL; + + strbuf_reset(&buf); + strbuf_addstr(&buf, oid_to_hex(&obj->oid)); + if (name) + strbuf_addf(&buf, " (%s)", name); + + return buf.buf; +} + +static const char *printable_type(struct object *obj) +{ + const char *ret; + + if (obj->type == OBJ_NONE) { + enum object_type type = oid_object_info(the_repository, + &obj->oid, NULL); + if (type > 0) + object_as_type(the_repository, obj, type, 0); + } + + ret = type_name(obj->type); + if (!ret) + ret = "unknown"; + + return ret; +} static int fsck_config(const char *var, const char *value, void *cb) { @@ -67,7 +109,7 @@ static void objreport(struct object *obj, const char *msg_type, const char *err) { fprintf(stderr, "%s in %s %s: %s\n", - msg_type, typename(obj->type), oid_to_hex(&obj->oid), err); + msg_type, printable_type(obj), describe_object(obj), err); } static int objerror(struct object *obj, const char *err) @@ -77,7 +119,8 @@ static int objerror(struct object *obj, const char *err) return -1; } -static int fsck_error_func(struct object *obj, int type, const char *message) +static int fsck_error_func(struct fsck_options *o, + struct object *obj, int type, const char *message) { objreport(obj, (type == FSCK_WARN) ? "warning" : "error", message); return (type == FSCK_WARN) ? 0 : 1; @@ -97,9 +140,9 @@ static int mark_object(struct object *obj, int type, void *data, struct fsck_opt if (!obj) { /* ... these references to parent->fld are safe here */ printf("broken link from %7s %s\n", - typename(parent->type), oid_to_hex(&parent->oid)); + printable_type(parent), describe_object(parent)); printf("broken link from %7s %s\n", - (type == OBJ_ANY ? "unknown" : typename(type)), "unknown"); + (type == OBJ_ANY ? "unknown" : type_name(type)), "unknown"); errors_found |= ERROR_REACHABLE; return 1; } @@ -111,12 +154,21 @@ static int mark_object(struct object *obj, int type, void *data, struct fsck_opt if (obj->flags & REACHABLE) return 0; obj->flags |= REACHABLE; + + if (is_promisor_object(&obj->oid)) + /* + * Further recursion does not need to be performed on this + * object since it is a promisor object (so it does not need to + * be added to "pending"). + */ + return 0; + if (!(obj->flags & HAS_OBJ)) { if (parent && !has_object_file(&obj->oid)) { printf("broken link from %7s %s\n", - typename(parent->type), oid_to_hex(&parent->oid)); + printable_type(parent), describe_object(parent)); printf(" to %7s %s\n", - typename(obj->type), oid_to_hex(&obj->oid)); + printable_type(obj), describe_object(obj)); errors_found |= ERROR_REACHABLE; } return 1; @@ -133,17 +185,12 @@ static void mark_object_reachable(struct object *obj) static int traverse_one_object(struct object *obj) { - int result; - struct tree *tree = NULL; + int result = fsck_walk(obj, obj, &fsck_walk_options); if (obj->type == OBJ_TREE) { - tree = (struct tree *)obj; - if (parse_tree(tree) < 0) - return 1; /* error already displayed */ - } - result = fsck_walk(obj, obj, &fsck_walk_options); - if (tree) + struct tree *tree = (struct tree *)obj; free_tree_buffer(tree); + } return result; } @@ -153,14 +200,9 @@ static int traverse_reachable(void) unsigned int nr = 0; int result = 0; if (show_progress) - progress = start_progress_delay(_("Checking connectivity"), 0, 0, 2); + progress = start_delayed_progress(_("Checking connectivity"), 0); while (pending.nr) { - struct object_array_entry *entry; - struct object *obj; - - entry = pending.objects + --pending.nr; - obj = entry->item; - result |= traverse_one_object(obj); + result |= traverse_one_object(object_array_pop(&pending)); display_progress(progress, ++nr); } stop_progress(&progress); @@ -171,7 +213,7 @@ static int mark_used(struct object *obj, int type, void *data, struct fsck_optio { if (!obj) return 1; - obj->used = 1; + obj->flags |= USED; return 0; } @@ -186,11 +228,12 @@ static void check_reachable_object(struct object *obj) * do a full fsck */ if (!(obj->flags & HAS_OBJ)) { - if (has_sha1_pack(obj->oid.hash)) - return; /* it is in pack - forget about it */ - if (connectivity_only && has_object_file(&obj->oid)) + if (is_promisor_object(&obj->oid)) return; - printf("missing %s %s\n", typename(obj->type), oid_to_hex(&obj->oid)); + if (has_object_pack(&obj->oid)) + return; /* it is in pack - forget about it */ + printf("missing %s %s\n", printable_type(obj), + describe_object(obj)); errors_found |= ERROR_REACHABLE; return; } @@ -207,7 +250,7 @@ static void check_unreachable_object(struct object *obj) * to complain about it being unreachable (since it does * not exist). */ - if (!obj->parsed) + if (!(obj->flags & HAS_OBJ)) return; /* @@ -215,12 +258,13 @@ static void check_unreachable_object(struct object *obj) * since this is something that is prunable. */ if (show_unreachable) { - printf("unreachable %s %s\n", typename(obj->type), oid_to_hex(&obj->oid)); + printf("unreachable %s %s\n", printable_type(obj), + describe_object(obj)); return; } /* - * "!used" means that nothing at all points to it, including + * "!USED" means that nothing at all points to it, including * other unreachable objects. In other words, it's the "tip" * of some set of unreachable objects, usually a commit that * got dropped. @@ -231,14 +275,14 @@ static void check_unreachable_object(struct object *obj) * deleted a branch by mistake, this is a prime candidate to * start looking at, for example. */ - if (!obj->used) { + if (!(obj->flags & USED)) { if (show_dangling) - printf("dangling %s %s\n", typename(obj->type), - oid_to_hex(&obj->oid)); + printf("dangling %s %s\n", printable_type(obj), + describe_object(obj)); if (write_lost_and_found) { char *filename = git_pathdup("lost-found/%s/%s", obj->type == OBJ_COMMIT ? "commit" : "other", - oid_to_hex(&obj->oid)); + describe_object(obj)); FILE *f; if (safe_create_leading_directories_const(filename)) { @@ -246,13 +290,12 @@ static void check_unreachable_object(struct object *obj) free(filename); return; } - if (!(f = fopen(filename, "w"))) - die_errno("Could not open '%s'", filename); + f = xfopen(filename, "w"); if (obj->type == OBJ_BLOB) { - if (stream_blob_to_fd(fileno(f), obj->oid.hash, NULL, 1)) + if (stream_blob_to_fd(fileno(f), &obj->oid, NULL, 1)) die_errno("Could not write '%s'", filename); } else - fprintf(f, "%s\n", oid_to_hex(&obj->oid)); + fprintf(f, "%s\n", describe_object(obj)); if (fclose(f)) die_errno("Could not finish '%s'", filename); @@ -271,7 +314,7 @@ static void check_unreachable_object(struct object *obj) static void check_object(struct object *obj) { if (verbose) - fprintf(stderr, "Checking %s\n", oid_to_hex(&obj->oid)); + fprintf(stderr, "Checking %s\n", describe_object(obj)); if (obj->flags & REACHABLE) check_reachable_object(obj); @@ -299,103 +342,104 @@ static void check_connectivity(void) } } -static int fsck_obj(struct object *obj) +static int fsck_obj(struct object *obj, void *buffer, unsigned long size) { + int err; + if (obj->flags & SEEN) return 0; obj->flags |= SEEN; if (verbose) fprintf(stderr, "Checking %s %s\n", - typename(obj->type), oid_to_hex(&obj->oid)); + printable_type(obj), describe_object(obj)); if (fsck_walk(obj, NULL, &fsck_obj_options)) objerror(obj, "broken links"); - if (fsck_object(obj, NULL, 0, &fsck_obj_options)) - return -1; - - if (obj->type == OBJ_TREE) { - struct tree *item = (struct tree *) obj; - - free_tree_buffer(item); - } + err = fsck_object(obj, buffer, size, &fsck_obj_options); + if (err) + goto out; if (obj->type == OBJ_COMMIT) { struct commit *commit = (struct commit *) obj; - free_commit_buffer(commit); - if (!commit->parents && show_root) - printf("root %s\n", oid_to_hex(&commit->object.oid)); + printf("root %s\n", describe_object(&commit->object)); } if (obj->type == OBJ_TAG) { struct tag *tag = (struct tag *) obj; if (show_tags && tag->tagged) { - printf("tagged %s %s", typename(tag->tagged->type), oid_to_hex(&tag->tagged->oid)); - printf(" (%s) in %s\n", tag->tag, oid_to_hex(&tag->object.oid)); + printf("tagged %s %s", printable_type(tag->tagged), + describe_object(tag->tagged)); + printf(" (%s) in %s\n", tag->tag, + describe_object(&tag->object)); } } - return 0; -} - -static int fsck_sha1(const unsigned char *sha1) -{ - struct object *obj = parse_object(sha1); - if (!obj) { - errors_found |= ERROR_OBJECT; - return error("%s: object corrupt or missing", - sha1_to_hex(sha1)); - } - obj->flags |= HAS_OBJ; - return fsck_obj(obj); +out: + if (obj->type == OBJ_TREE) + free_tree_buffer((struct tree *)obj); + if (obj->type == OBJ_COMMIT) + free_commit_buffer((struct commit *)obj); + return err; } -static int fsck_obj_buffer(const unsigned char *sha1, enum object_type type, +static int fsck_obj_buffer(const struct object_id *oid, enum object_type type, unsigned long size, void *buffer, int *eaten) { + /* + * Note, buffer may be NULL if type is OBJ_BLOB. See + * verify_packfile(), data_valid variable for details. + */ struct object *obj; - obj = parse_object_buffer(sha1, type, size, buffer, eaten); + obj = parse_object_buffer(the_repository, oid, type, size, buffer, + eaten); if (!obj) { errors_found |= ERROR_OBJECT; - return error("%s: object corrupt or missing", sha1_to_hex(sha1)); + return error("%s: object corrupt or missing", oid_to_hex(oid)); } - obj->flags = HAS_OBJ; - return fsck_obj(obj); + obj->flags &= ~(REACHABLE | SEEN); + obj->flags |= HAS_OBJ; + return fsck_obj(obj, buffer, size); } static int default_refs; -static void fsck_handle_reflog_sha1(const char *refname, unsigned char *sha1) +static void fsck_handle_reflog_oid(const char *refname, struct object_id *oid, + timestamp_t timestamp) { struct object *obj; - if (!is_null_sha1(sha1)) { - obj = lookup_object(sha1); - if (obj) { - obj->used = 1; + if (!is_null_oid(oid)) { + obj = lookup_object(the_repository, oid->hash); + if (obj && (obj->flags & HAS_OBJ)) { + if (timestamp && name_objects) + add_decoration(fsck_walk_options.object_names, + obj, + xstrfmt("%s@{%"PRItime"}", refname, timestamp)); + obj->flags |= USED; mark_object_reachable(obj); - } else { - error("%s: invalid reflog entry %s", refname, sha1_to_hex(sha1)); + } else if (!is_promisor_object(oid)) { + error("%s: invalid reflog entry %s", refname, oid_to_hex(oid)); errors_found |= ERROR_REACHABLE; } } } -static int fsck_handle_reflog_ent(unsigned char *osha1, unsigned char *nsha1, - const char *email, unsigned long timestamp, int tz, +static int fsck_handle_reflog_ent(struct object_id *ooid, struct object_id *noid, + const char *email, timestamp_t timestamp, int tz, const char *message, void *cb_data) { const char *refname = cb_data; if (verbose) fprintf(stderr, "Checking reflog %s->%s\n", - sha1_to_hex(osha1), sha1_to_hex(nsha1)); + oid_to_hex(ooid), oid_to_hex(noid)); - fsck_handle_reflog_sha1(refname, osha1); - fsck_handle_reflog_sha1(refname, nsha1); + fsck_handle_reflog_oid(refname, ooid, 0); + fsck_handle_reflog_oid(refname, noid, timestamp); return 0; } @@ -411,8 +455,16 @@ static int fsck_handle_ref(const char *refname, const struct object_id *oid, { struct object *obj; - obj = parse_object(oid->hash); + obj = parse_object(the_repository, oid); if (!obj) { + if (is_promisor_object(oid)) { + /* + * Increment default_refs anyway, because this is a + * valid ref. + */ + default_refs++; + return 0; + } error("%s: invalid sha1 pointer %s", refname, oid_to_hex(oid)); errors_found |= ERROR_REACHABLE; /* We'll continue with the rest despite the error.. */ @@ -423,7 +475,10 @@ static int fsck_handle_ref(const char *refname, const struct object_id *oid, errors_found |= ERROR_REFS; } default_refs++; - obj->used = 1; + obj->flags |= USED; + if (name_objects) + add_decoration(fsck_walk_options.object_names, + obj, xstrdup(refname)); mark_object_reachable(obj); return 0; @@ -455,11 +510,44 @@ static void get_default_heads(void) } } -static int fsck_loose(const unsigned char *sha1, const char *path, void *data) +static int fsck_loose(const struct object_id *oid, const char *path, void *data) { - if (fsck_sha1(sha1)) + struct object *obj; + enum object_type type; + unsigned long size; + void *contents; + int eaten; + + if (read_loose_object(path, oid, &type, &size, &contents) < 0) { errors_found |= ERROR_OBJECT; - return 0; + error("%s: object corrupt or missing: %s", + oid_to_hex(oid), path); + return 0; /* keep checking other objects */ + } + + if (!contents && type != OBJ_BLOB) + BUG("read_loose_object streamed a non-blob"); + + obj = parse_object_buffer(the_repository, oid, type, size, + contents, &eaten); + + if (!obj) { + errors_found |= ERROR_OBJECT; + error("%s: object could not be parsed: %s", + oid_to_hex(oid), path); + if (!eaten) + free(contents); + return 0; /* keep checking other objects */ + } + + obj->flags &= ~(REACHABLE | SEEN); + obj->flags |= HAS_OBJ; + if (fsck_obj(obj, contents, size)) + errors_found |= ERROR_OBJECT; + + if (!eaten) + free(contents); + return 0; /* keep checking other objects, even if we saw an error */ } static int fsck_cruft(const char *basename, const char *path, void *data) @@ -469,7 +557,7 @@ static int fsck_cruft(const char *basename, const char *path, void *data) return 0; } -static int fsck_subdir(int nr, const char *path, void *progress) +static int fsck_subdir(unsigned int nr, const char *path, void *progress) { display_progress(progress, nr + 1); return 0; @@ -498,7 +586,7 @@ static int fsck_head_link(void) if (verbose) fprintf(stderr, "Checking HEAD link\n"); - head_points_at = resolve_ref_unsafe("HEAD", 0, head_oid.hash, NULL); + head_points_at = resolve_ref_unsafe("HEAD", 0, &head_oid, NULL); if (!head_points_at) { errors_found |= ERROR_REFS; return error("Invalid HEAD"); @@ -531,14 +619,17 @@ static int fsck_cache_tree(struct cache_tree *it) fprintf(stderr, "Checking cache tree\n"); if (0 <= it->entry_count) { - struct object *obj = parse_object(it->sha1); + struct object *obj = parse_object(the_repository, &it->oid); if (!obj) { error("%s: invalid sha1 pointer in cache-tree", - sha1_to_hex(it->sha1)); + oid_to_hex(&it->oid)); errors_found |= ERROR_REFS; return 1; } - obj->used = 1; + obj->flags |= USED; + if (name_objects) + add_decoration(fsck_walk_options.object_names, + obj, xstrdup(":")); mark_object_reachable(obj); if (obj->type != OBJ_TREE) err |= objerror(obj, "non-tree in cache-tree"); @@ -548,6 +639,29 @@ static int fsck_cache_tree(struct cache_tree *it) return err; } +static void mark_object_for_connectivity(const struct object_id *oid) +{ + struct object *obj = lookup_unknown_object(oid->hash); + obj->flags |= HAS_OBJ; +} + +static int mark_loose_for_connectivity(const struct object_id *oid, + const char *path, + void *data) +{ + mark_object_for_connectivity(oid); + return 0; +} + +static int mark_packed_for_connectivity(const struct object_id *oid, + struct packed_git *pack, + uint32_t pos, + void *data) +{ + mark_object_for_connectivity(oid); + return 0; +} + static char const * const fsck_usage[] = { N_("git fsck [<options>] [<object>...]"), NULL @@ -567,16 +681,20 @@ static struct option fsck_opts[] = { OPT_BOOL(0, "lost-found", &write_lost_and_found, N_("write dangling objects in .git/lost-found")), OPT_BOOL(0, "progress", &show_progress, N_("show progress")), + OPT_BOOL(0, "name-objects", &name_objects, N_("show verbose names for reachable objects")), OPT_END(), }; int cmd_fsck(int argc, const char **argv, const char *prefix) { - int i, heads; + int i; struct alternate_object_database *alt; + /* fsck knows how to handle missing promisor objects */ + fetch_if_missing = 0; + errors_found = 0; - check_replace_refs = 0; + read_replace_refs = 0; argc = parse_options(argc, argv, prefix, fsck_opts, fsck_usage, 0); @@ -596,66 +714,80 @@ int cmd_fsck(int argc, const char **argv, const char *prefix) include_reflogs = 0; } + if (name_objects) + fsck_walk_options.object_names = + xcalloc(1, sizeof(struct decoration)); + git_config(fsck_config, NULL); fsck_head_link(); - if (!connectivity_only) { - fsck_object_dir(get_object_directory()); - - prepare_alt_odb(); - for (alt = alt_odb_list; alt; alt = alt->next) { - /* directory name, minus trailing slash */ - size_t namelen = alt->name - alt->base - 1; - struct strbuf name = STRBUF_INIT; - strbuf_add(&name, alt->base, namelen); - fsck_object_dir(name.buf); - strbuf_release(&name); - } - } - - if (check_full) { - struct packed_git *p; - uint32_t total = 0, count = 0; - struct progress *progress = NULL; + if (connectivity_only) { + for_each_loose_object(mark_loose_for_connectivity, NULL, 0); + for_each_packed_object(mark_packed_for_connectivity, NULL, 0); + } else { + struct alternate_object_database *alt_odb_list; - prepare_packed_git(); + fsck_object_dir(get_object_directory()); - if (show_progress) { - for (p = packed_git; p; p = p->next) { - if (open_pack_index(p)) - continue; - total += p->num_objects; + prepare_alt_odb(the_repository); + alt_odb_list = the_repository->objects->alt_odb_list; + for (alt = alt_odb_list; alt; alt = alt->next) + fsck_object_dir(alt->path); + + if (check_full) { + struct packed_git *p; + uint32_t total = 0, count = 0; + struct progress *progress = NULL; + + if (show_progress) { + for (p = get_all_packs(the_repository); p; + p = p->next) { + if (open_pack_index(p)) + continue; + total += p->num_objects; + } + + progress = start_progress(_("Checking objects"), total); } - - progress = start_progress(_("Checking objects"), total); - } - for (p = packed_git; p; p = p->next) { - /* verify gives error messages itself */ - if (verify_pack(p, fsck_obj_buffer, - progress, count)) - errors_found |= ERROR_PACK; - count += p->num_objects; + for (p = get_all_packs(the_repository); p; + p = p->next) { + /* verify gives error messages itself */ + if (verify_pack(p, fsck_obj_buffer, + progress, count)) + errors_found |= ERROR_PACK; + count += p->num_objects; + } + stop_progress(&progress); } - stop_progress(&progress); + + if (fsck_finish(&fsck_obj_options)) + errors_found |= ERROR_OBJECT; } - heads = 0; for (i = 0; i < argc; i++) { const char *arg = argv[i]; - unsigned char sha1[20]; - if (!get_sha1(arg, sha1)) { - struct object *obj = lookup_object(sha1); + struct object_id oid; + if (!get_oid(arg, &oid)) { + struct object *obj = lookup_object(the_repository, + oid.hash); - /* Error is printed by lookup_object(). */ - if (!obj) + if (!obj || !(obj->flags & HAS_OBJ)) { + if (is_promisor_object(&oid)) + continue; + error("%s: object missing", oid_to_hex(&oid)); + errors_found |= ERROR_OBJECT; continue; + } - obj->used = 1; + obj->flags |= USED; + if (name_objects) + add_decoration(fsck_walk_options.object_names, + obj, xstrdup(arg)); mark_object_reachable(obj); - heads++; continue; } error("invalid parameter: expected sha1, got '%s'", arg); + errors_found |= ERROR_OBJECT; } /* @@ -663,12 +795,14 @@ int cmd_fsck(int argc, const char **argv, const char *prefix) * default ones from .git/refs. We also consider the index file * in this case (ie this implies --cache). */ - if (!heads) { + if (!argc) { get_default_heads(); keep_cache_objects = 1; } if (keep_cache_objects) { + verify_index_checksum = 1; + verify_ce_order = 1; read_cache(); for (i = 0; i < active_nr; i++) { unsigned int mode; @@ -678,11 +812,16 @@ int cmd_fsck(int argc, const char **argv, const char *prefix) mode = active_cache[i]->ce_mode; if (S_ISGITLINK(mode)) continue; - blob = lookup_blob(active_cache[i]->sha1); + blob = lookup_blob(the_repository, + &active_cache[i]->oid); if (!blob) continue; obj = &blob->object; - obj->used = 1; + obj->flags |= USED; + if (name_objects) + add_decoration(fsck_walk_options.object_names, + obj, + xstrfmt(":%s", active_cache[i]->name)); mark_object_reachable(obj); } if (active_cache_tree) @@ -690,5 +829,42 @@ int cmd_fsck(int argc, const char **argv, const char *prefix) } check_connectivity(); + + if (!git_config_get_bool("core.commitgraph", &i) && i) { + struct child_process commit_graph_verify = CHILD_PROCESS_INIT; + const char *verify_argv[] = { "commit-graph", "verify", NULL, NULL, NULL }; + + commit_graph_verify.argv = verify_argv; + commit_graph_verify.git_cmd = 1; + if (run_command(&commit_graph_verify)) + errors_found |= ERROR_COMMIT_GRAPH; + + prepare_alt_odb(the_repository); + for (alt = the_repository->objects->alt_odb_list; alt; alt = alt->next) { + verify_argv[2] = "--object-dir"; + verify_argv[3] = alt->path; + if (run_command(&commit_graph_verify)) + errors_found |= ERROR_COMMIT_GRAPH; + } + } + + if (!git_config_get_bool("core.multipackindex", &i) && i) { + struct child_process midx_verify = CHILD_PROCESS_INIT; + const char *midx_argv[] = { "multi-pack-index", "verify", NULL, NULL, NULL }; + + midx_verify.argv = midx_argv; + midx_verify.git_cmd = 1; + if (run_command(&midx_verify)) + errors_found |= ERROR_COMMIT_GRAPH; + + prepare_alt_odb(the_repository); + for (alt = the_repository->objects->alt_odb_list; alt; alt = alt->next) { + midx_argv[2] = "--object-dir"; + midx_argv[3] = alt->path; + if (run_command(&midx_verify)) + errors_found |= ERROR_COMMIT_GRAPH; + } + } + return errors_found; } |