@@ -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);
@@ -603,20 +603,25 @@ 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;
@@ -1419,7 +1419,7 @@ 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));
/*
@@ -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;
@@ -1062,9 +1062,11 @@ 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;
@@ -1072,8 +1074,8 @@ 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);
@@ -1098,9 +1100,9 @@ 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_oid_fn(&real_oid, &c);
+ r->hash_algo->final_oid_fn(real_oid, &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)
@@ -2560,6 +2562,7 @@ 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)
@@ -2609,9 +2612,9 @@ 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;
}
@@ -392,6 +392,7 @@ 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);
@@ -528,7 +529,8 @@ enum unpack_loose_header_result unpack_loose_header(git_zstream *stream,
int parse_loose_header(const char *hdr, struct object_info *oi);
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);
@@ -279,7 +279,7 @@ 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;
}
@@ -290,7 +290,7 @@ 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;
@@ -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) {
@@ -490,7 +490,7 @@ test_expect_success 'cat-file -t and -s on corrupt loose object' '
# Swap the two to corrupt the repository
mv -f "$other_path" "$empty_path" &&
test_must_fail git fsck 2>err.fsck &&
- grep "hash mismatch" err.fsck &&
+ grep "hash-path mismatch" err.fsck &&
# confirm that cat-file is reading the new swapped-in
# blob...
@@ -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
)
'
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 </dev/null e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 $ mv objects/e6/ objects/e7 Would emit ("[...]" used to abbreviate the OIDs): git fsck error: hash mismatch for ./objects/e7/9d[...] (expected e79d[...]) error: e79d[...]: object corrupt or missing: ./objects/e7/9d[...] Now we'll instead emit: error: e69d[...]: hash-path mismatch, found at: ./objects/e7/9d[...] Furthermore, we'll do the right thing when the object type and its location are bad. I.e. this case: $ git hash-object --stdin -w -t garbage --literally </dev/null 8315a83d2acc4c174aed59430f9a9c4ed926440f $ mv objects/83 objects/84 As noted in an earlier commits we'd simply die early in those cases, until preceding commits fixed the hard die on invalid object type: $ git fsck fatal: invalid object type Now we'll instead emit sensible error messages: $ git fsck error: 8315[...]: hash-path mismatch, found at: ./objects/84/15[...] error: 8315[...]: object is of unknown type 'garbage': ./objects/84/15[...] In both fsck.c and object-file.c we're using null_oid as a sentinel value for checking whether we got far enough to be certain that the issue was indeed this OID mismatch. In the case of check_object_signature() I don't really trust all the moving parts there to behave consistently, in the face of future refactorings. Getting it wrong would mean that we'd potentially emit no error at all on a failing check_object_signature(), or worse misreport whatever issue we encountered. So let's use the new bug() function to ferry and return code up to fsck_loose() in that case. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> --- 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/t1006-cat-file.sh | 2 +- t/t1450-fsck.sh | 8 +++++--- 10 files changed, 38 insertions(+), 24 deletions(-)