From: Ævar Arnfjörð Bjarmason Date: Tue, 13 Apr 2021 09:43:09 GMT Subject: [PATCH v2 6/6] fsck: report invalid object type-path combinations Message-ID: In-Reply-To: fsck: improve error on loose object hash mismatch Improve the error that's emitted in cases where we find a loose object we parse, but which isn't at the location we expect it to be. Before this change we'd prefix the error with a not-a-OID derived from the path at which the object was found, due to an emergent behavior in how we'd end up with an "OID" in these codepaths. Now we'll instead say what object we hashed, and what path it was found at. Before this patch series e.g.: $ git hash-object --stdin -w -t blob --- builtin/fast-export.c | 2 +- builtin/fsck.c | 13 +++++++++---- builtin/index-pack.c | 2 +- builtin/mktag.c | 3 ++- object-file.c | 21 ++++++++++++--------- object-store.h | 4 +++- object.c | 4 ++-- pack-check.c | 3 ++- t/t1450-fsck.sh | 8 +++++--- 9 files changed, 37 insertions(+), 23 deletions(-) diff --git a/builtin/fast-export.c b/builtin/fast-export.c index 85a76e0ef8b..bf0e266d83a 100644 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@ -312,7 +312,7 @@ static void export_blob(const struct object_id *oid) if (!buf) die("could not read blob %s", oid_to_hex(oid)); if (check_object_signature(the_repository, oid, buf, size, - type_name(type)) < 0) + type_name(type), NULL) < 0) die("oid mismatch in blob %s", oid_to_hex(oid)); object = parse_object_buffer(the_repository, oid, type, size, buf, &eaten); diff --git a/builtin/fsck.c b/builtin/fsck.c index 878191e53ca..7713d992960 100644 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@ -602,20 +602,25 @@ static int fsck_loose(const struct object_id *oid, const char *path, void *data) struct strbuf sb = STRBUF_INIT; unsigned int oi_flags = OBJECT_INFO_ALLOW_UNKNOWN_TYPE; struct object_info oi; + struct object_id real_oid = null_oid; int found = 0; oi.type_name = &sb; oi.sizep = &size; oi.typep = &type; - if (read_loose_object(path, oid, &contents, &oi, oi_flags) < 0) { + if (read_loose_object(path, oid, &real_oid, &contents, &oi, oi_flags) < 0) { found |= ERROR_OBJECT; - error(_("%s: object corrupt or missing: %s"), - oid_to_hex(oid), path); + if (!oideq(&real_oid, oid)) + error(_("%s: hash-path mismatch, found at: %s"), + oid_to_hex(&real_oid), path); + else + error(_("%s: object corrupt or missing: %s"), + oid_to_hex(oid), path); } if (type < 0) { found |= ERROR_OBJECT; error(_("%s: object is of unknown type '%s': %s"), - oid_to_hex(oid), sb.buf, path); + oid_to_hex(&real_oid), sb.buf, path); } if (found) { errors_found |= ERROR_OBJECT; diff --git a/builtin/index-pack.c b/builtin/index-pack.c index 15507b5cff0..d5fd81ebf39 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -1421,7 +1421,7 @@ static void fix_unresolved_deltas(struct hashfile *f) if (check_object_signature(the_repository, &d->oid, data, size, - type_name(type))) + type_name(type), NULL)) die(_("local object %s is corrupt"), oid_to_hex(&d->oid)); /* diff --git a/builtin/mktag.c b/builtin/mktag.c index dddcccdd368..3b2dbbb37e6 100644 --- a/builtin/mktag.c +++ b/builtin/mktag.c @@ -62,7 +62,8 @@ static int verify_object_in_tag(struct object_id *tagged_oid, int *tagged_type) repl = lookup_replace_object(the_repository, tagged_oid); ret = check_object_signature(the_repository, repl, - buffer, size, type_name(*tagged_type)); + buffer, size, type_name(*tagged_type), + NULL); free(buffer); return ret; diff --git a/object-file.c b/object-file.c index e744a06637b..ca54e76fda2 100644 --- a/object-file.c +++ b/object-file.c @@ -993,9 +993,11 @@ void *xmmap(void *start, size_t length, * the streaming interface and rehash it to do the same. */ int check_object_signature(struct repository *r, const struct object_id *oid, - void *map, unsigned long size, const char *type) + void *map, unsigned long size, const char *type, + struct object_id *real_oidp) { - struct object_id real_oid; + struct object_id tmp; + struct object_id *real_oid = real_oidp ? real_oidp : &tmp; enum object_type obj_type; struct git_istream *st; git_hash_ctx c; @@ -1003,8 +1005,8 @@ int check_object_signature(struct repository *r, const struct object_id *oid, int hdrlen; if (map) { - hash_object_file(r->hash_algo, map, size, type, &real_oid); - return !oideq(oid, &real_oid) ? -1 : 0; + hash_object_file(r->hash_algo, map, size, type, real_oid); + return !oideq(oid, real_oid) ? -1 : 0; } st = open_istream(r, oid, &obj_type, &size, NULL); @@ -1029,9 +1031,9 @@ int check_object_signature(struct repository *r, const struct object_id *oid, break; r->hash_algo->update_fn(&c, buf, readlen); } - r->hash_algo->final_fn(real_oid.hash, &c); + r->hash_algo->final_fn(real_oid->hash, &c); close_istream(st); - return !oideq(oid, &real_oid) ? -1 : 0; + return !oideq(oid, real_oid) ? -1 : 0; } int git_open_cloexec(const char *name, int flags) @@ -2489,6 +2491,7 @@ static int check_stream_oid(git_zstream *stream, int read_loose_object(const char *path, const struct object_id *expected_oid, + struct object_id *real_oid, void **contents, struct object_info *oi, unsigned int oi_flags) @@ -2532,9 +2535,9 @@ int read_loose_object(const char *path, goto out; } if (check_object_signature(the_repository, expected_oid, - *contents, *size, oi->type_name->buf)) { - error(_("hash mismatch for %s (expected %s)"), path, - oid_to_hex(expected_oid)); + *contents, *size, oi->type_name->buf, real_oid)) { + if (oideq(real_oid, &null_oid)) + BUG("should only get OID mismatch errors with mapped contents"); free(*contents); goto out; } diff --git a/object-store.h b/object-store.h index 3d88b8a7cd3..c9c4d211de3 100644 --- a/object-store.h +++ b/object-store.h @@ -384,6 +384,7 @@ int oid_object_info_extended(struct repository *r, */ int read_loose_object(const char *path, const struct object_id *expected_oid, + struct object_id *real_oid, void **contents, struct object_info *oi, unsigned int oi_flags); @@ -484,7 +485,8 @@ int unpack_loose_header(git_zstream *stream, unsigned char *map, int parse_loose_header(const char *hdr, struct object_info *oi, unsigned int flags); int check_object_signature(struct repository *r, const struct object_id *oid, - void *buf, unsigned long size, const char *type); + void *buf, unsigned long size, const char *type, + struct object_id *real_oidp); int finalize_object_file(const char *tmpfile, const char *filename); int check_and_freshen_file(const char *fn, int freshen); diff --git a/object.c b/object.c index 78343781ae7..1cb4b30acd7 100644 --- a/object.c +++ b/object.c @@ -262,7 +262,7 @@ struct object *parse_object(struct repository *r, const struct object_id *oid) if ((obj && obj->type == OBJ_BLOB && repo_has_object_file(r, oid)) || (!obj && repo_has_object_file(r, oid) && oid_object_info(r, oid, NULL) == OBJ_BLOB)) { - if (check_object_signature(r, repl, NULL, 0, NULL) < 0) { + if (check_object_signature(r, repl, NULL, 0, NULL, NULL) < 0) { error(_("hash mismatch %s"), oid_to_hex(oid)); return NULL; } @@ -273,7 +273,7 @@ struct object *parse_object(struct repository *r, const struct object_id *oid) buffer = repo_read_object_file(r, oid, &type, &size); if (buffer) { if (check_object_signature(r, repl, buffer, size, - type_name(type)) < 0) { + type_name(type), NULL) < 0) { free(buffer); error(_("hash mismatch %s"), oid_to_hex(repl)); return NULL; diff --git a/pack-check.c b/pack-check.c index 4b089fe8ec0..e6aa4442c90 100644 --- a/pack-check.c +++ b/pack-check.c @@ -142,7 +142,8 @@ static int verify_packfile(struct repository *r, err = error("cannot unpack %s from %s at offset %"PRIuMAX"", oid_to_hex(&oid), p->pack_name, (uintmax_t)entries[i].offset); - else if (check_object_signature(r, &oid, data, size, type_name(type))) + else if (check_object_signature(r, &oid, data, size, + type_name(type), NULL)) err = error("packed %s from %s is corrupt", oid_to_hex(&oid), p->pack_name); else if (fn) { diff --git a/t/t1450-fsck.sh b/t/t1450-fsck.sh index 214278e134a..c7b084364b7 100755 --- a/t/t1450-fsck.sh +++ b/t/t1450-fsck.sh @@ -53,6 +53,7 @@ test_expect_success 'object with hash mismatch' ' ( cd hash-mismatch && oid=$(echo blob | git hash-object -w --stdin) && + oldoid=$oid && old=$(test_oid_to_path "$oid") && new=$(dirname $old)/$(test_oid ff_2) && oid="$(dirname $new)$(basename $new)" && @@ -62,7 +63,7 @@ test_expect_success 'object with hash mismatch' ' cmt=$(echo bogus | git commit-tree $tree) && git update-ref refs/heads/bogus $cmt && test_must_fail git fsck 2>out && - test_i18ngrep "$oid.*corrupt" out + grep "$oldoid: hash-path mismatch, found at: .*$new" out ) ' @@ -71,6 +72,7 @@ test_expect_success 'object with hash and type mismatch' ' ( cd hash-type-mismatch && oid=$(echo blob | git hash-object -w --stdin -t garbage --literally) && + oldoid=$oid && old=$(test_oid_to_path "$oid") && new=$(dirname $old)/$(test_oid ff_2) && oid="$(dirname $new)$(basename $new)" && @@ -80,8 +82,8 @@ test_expect_success 'object with hash and type mismatch' ' cmt=$(echo bogus | git commit-tree $tree) && git update-ref refs/heads/bogus $cmt && test_must_fail git fsck 2>out && - grep "^error: hash mismatch for " out && - grep "^error: $oid: object is of unknown type '"'"'garbage'"'"'" out + grep "^error: $oldoid: hash-path mismatch, found at: .*$new" out && + grep "^error: $oldoid: object is of unknown type '"'"'garbage'"'"'" out ) ' -- 2.31.1.645.g989d83ea6a6