[PATCH v3 16/17] fsck: report invalid types recorded in objects

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Continue the work in the preceding commit and improve the error on:

    $ git hash-object --stdin -w -t garbage --literally </dev/null
    $ git fsck
    error: hash mismatch for <OID_PATH> (expected <OID>)
    error: <OID>: object corrupt or missing: <OID_PATH>
    [ other fsck output ]

To instead emit:

    $ git fsck
    error: <OID>: object is of unknown type 'garbage': <OID_PATH>
    [ other fsck output ]

The complaint about a "hash mismatch" was simply an emergent property
of how we'd fall though from read_loose_object() into fsck_loose()
when we didn't get the data we expected. Now we'll correctly note that
the object type is invalid.

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@xxxxxxxxx>
---
 builtin/fsck.c  | 22 ++++++++++++++++++----
 object-file.c   | 13 +++++--------
 object-store.h  |  4 ++--
 t/t1450-fsck.sh | 24 +++++++++++++++++++++---
 4 files changed, 46 insertions(+), 17 deletions(-)

diff --git a/builtin/fsck.c b/builtin/fsck.c
index 38b515deb6..32f11dc1fe 100644
--- a/builtin/fsck.c
+++ b/builtin/fsck.c
@@ -599,12 +599,26 @@ static int fsck_loose(const struct object_id *oid, const char *path, void *data)
 	unsigned long size;
 	void *contents;
 	int eaten;
-
-	if (read_loose_object(path, oid, &type, &size, &contents,
-			      OBJECT_INFO_ALLOW_UNKNOWN_TYPE) < 0) {
-		errors_found |= ERROR_OBJECT;
+	struct strbuf sb = STRBUF_INIT;
+	unsigned int oi_flags = OBJECT_INFO_ALLOW_UNKNOWN_TYPE;
+	struct object_info oi;
+	int found = 0;
+	oi.type_name = &sb;
+	oi.sizep = &size;
+	oi.typep = &type;
+
+	if (read_loose_object(path, oid, &contents, &oi, oi_flags) < 0) {
+		found |= ERROR_OBJECT;
 		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);
+	}
+	if (found) {
+		errors_found |= ERROR_OBJECT;
 		return 0; /* keep checking other objects */
 	}
 
diff --git a/object-file.c b/object-file.c
index 0e8a024eb3..f24fa2fe4a 100644
--- a/object-file.c
+++ b/object-file.c
@@ -2520,9 +2520,8 @@ static int check_stream_oid(git_zstream *stream,
 
 int read_loose_object(const char *path,
 		      const struct object_id *expected_oid,
-		      enum object_type *type,
-		      unsigned long *size,
 		      void **contents,
+		      struct object_info *oi,
 		      unsigned int oi_flags)
 {
 	int ret = -1;
@@ -2530,10 +2529,9 @@ int read_loose_object(const char *path,
 	unsigned long mapsize;
 	git_zstream stream;
 	char hdr[MAX_HEADER_LEN];
-	struct object_info oi = OBJECT_INFO_INIT;
 	int allow_unknown = oi_flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE;
-	oi.typep = type;
-	oi.sizep = size;
+	enum object_type *type = oi->typep;
+	unsigned long *size = oi->sizep;
 
 	*contents = NULL;
 
@@ -2549,7 +2547,7 @@ int read_loose_object(const char *path,
 		goto out;
 	}
 
-	if (parse_loose_header(hdr, &oi) < 0) {
+	if (parse_loose_header(hdr, oi) < 0) {
 		error(_("unable to parse header of %s"), path);
 		git_inflate_end(&stream);
 		goto out;
@@ -2571,8 +2569,7 @@ int read_loose_object(const char *path,
 			goto out;
 		}
 		if (check_object_signature(the_repository, expected_oid,
-					   *contents, *size,
-					   type_name(*type))) {
+					   *contents, *size, oi->type_name->buf)) {
 			error(_("hash mismatch for %s (expected %s)"), path,
 			      oid_to_hex(expected_oid));
 			free(*contents);
diff --git a/object-store.h b/object-store.h
index 698a701d70..ba6e5d76c0 100644
--- a/object-store.h
+++ b/object-store.h
@@ -376,6 +376,7 @@ int oid_object_info_extended(struct repository *r,
 
 /*
  * 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.
  *
@@ -383,9 +384,8 @@ int oid_object_info_extended(struct repository *r,
  */
 int read_loose_object(const char *path,
 		      const struct object_id *expected_oid,
-		      enum object_type *type,
-		      unsigned long *size,
 		      void **contents,
+		      struct object_info *oi,
 		      unsigned int oi_flags);
 
 /*
diff --git a/t/t1450-fsck.sh b/t/t1450-fsck.sh
index e7e8decebb..bc541af2cf 100755
--- a/t/t1450-fsck.sh
+++ b/t/t1450-fsck.sh
@@ -66,6 +66,25 @@ test_expect_success 'object with hash mismatch' '
 	)
 '
 
+test_expect_success 'object with hash and type mismatch' '
+	test_create_repo hash-type-mismatch &&
+	(
+		cd hash-type-mismatch &&
+		oid=$(echo blob | git hash-object -w --stdin -t garbage --literally) &&
+		old=$(test_oid_to_path "$oid") &&
+		new=$(dirname $old)/$(test_oid ff_2) &&
+		oid="$(dirname $new)$(basename $new)" &&
+		mv .git/objects/$old .git/objects/$new &&
+		git update-index --add --cacheinfo 100644 $oid foo &&
+		tree=$(git write-tree) &&
+		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: $oid: object is of unknown type '"'"'garbage'"'"'" out
+	)
+'
+
 test_expect_success 'branch pointing to non-commit' '
 	git rev-parse HEAD^{tree} >.git/refs/heads/invalid &&
 	test_when_finished "git update-ref -d refs/heads/invalid" &&
@@ -869,9 +888,8 @@ test_expect_success 'fsck error and recovery on invalid object type' '
 	garbage_blob=$(git -C garbage-type hash-object --stdin -w -t garbage --literally </dev/null) &&
 	test_must_fail git -C garbage-type fsck >out 2>err &&
 	grep -e "^error" -e "^fatal" err >errors &&
-	test_line_count = 2 errors &&
-	grep "error: hash mismatch for" err &&
-	grep "$garbage_blob: object corrupt or missing:" err &&
+	test_line_count = 1 errors &&
+	grep "$garbage_blob: object is of unknown type '"'"'garbage'"'"':" err &&
 	grep "dangling blob $empty_blob" out
 '
 
-- 
2.32.0.rc0.406.g73369325f8d




[Index of Archives]     [Linux Kernel Development]     [Gcc Help]     [IETF Annouce]     [DCCP]     [Netdev]     [Networking]     [Security]     [V4L]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux SCSI]     [Fedora Users]

  Powered by Linux