[PATCH 4/4] fsck: validate .rev file header

From: Derrick Stolee via GitGitGadget <gitgitgadget@gmail.com>
Date: Apr 17, 2023, 16:21 UTC
Message-ID: <7d894d859ef109091b86bc4e2e4f6cea0e808370.1681748502.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.1512.git.1681748502.gitgitgadget@gmail.com>

From: Derrick Stolee <derrickstolee@github.com>

While parsing a .rev file, we check the header information to be sure it makes sense. This happens before doing any additional validation such as a checksum or value check. In order to differentiate between a bad header and a non-existent file, we need to update the API for loading a reverse index.

Make load_pack_revindex_from_disk() non-static and specify that a positive value means "the file does not exist" while other errors during parsing are negative values. Since an invalid header prevents setting up the structures we would use for further validations, we can stop at that point.

The place where we can distinguish between a missing file and a corrupt file is inside load_revindex_from_disk(), which is used both by pack rev-indexes and multi-pack-index rev-indexes. Some tests in t5326 demonstrate that it is critical to take some conditions to allow positive error signals.

Add tests that check the three header values.

Signed-off-by: Derrick Stolee <derrickstolee@github.com>
---
 builtin/fsck.c           | 10 ++++++++--
 pack-bitmap.c            |  4 ++--
 pack-revindex.c          |  5 +++--
 pack-revindex.h          |  8 ++++++++
 t/t5325-reverse-index.sh | 15 +++++++++++++++
 5 files changed, 36 insertions(+), 6 deletions(-)

diff --git a/builtin/fsck.c b/builtin/fsck.c
index 2ab78129bde..2414190c049 100644
--- a/builtin/fsck.c
+++ b/builtin/fsck.c
@@ -872,8 +872,14 @@ static int check_pack_rev_indexes(struct repository *r, int show_progress)
 	}
 
 	for (struct packed_git *p = get_all_packs(the_repository); p; p = p->next) {
-		if (!load_pack_revindex(the_repository, p) &&
-		    verify_pack_revindex(p)) {
+		int load_error = load_pack_revindex_from_disk(p);
+
+		if (load_error < 0) {
+			error(_("unable to load rev-index for pack '%s'"), p->pack_name);
+			res = ERROR_PACK_REV_INDEX;
+		} else if (!load_error &&
+			   !load_pack_revindex(the_repository, p) &&
+			   verify_pack_revindex(p)) {
 			error(_("invalid rev-index for pack '%s'"), p->pack_name);
 			res = ERROR_PACK_REV_INDEX;
 		}
diff --git a/pack-bitmap.c b/pack-bitmap.c
index 38b35c48237..3828aab612a 100644
--- a/pack-bitmap.c
+++ b/pack-bitmap.c
@@ -379,7 +379,7 @@ static int open_midx_bitmap_1(struct bitmap_index *bitmap_git,
 		goto cleanup;
 	}
 
-	if (load_midx_revindex(bitmap_git->midx) < 0) {
+	if (load_midx_revindex(bitmap_git->midx)) {
 		warning(_("multi-pack bitmap is missing required reverse index"));
 		goto cleanup;
 	}
@@ -2140,7 +2140,7 @@ uint32_t *create_bitmap_mapping(struct bitmap_index *bitmap_git,
 
 	if (!bitmap_is_midx(bitmap_git))
 		load_reverse_index(r, bitmap_git);
-	else if (load_midx_revindex(bitmap_git->midx) < 0)
+	else if (load_midx_revindex(bitmap_git->midx))
 		BUG("rebuild_existing_bitmaps: missing required rev-cache "
 		    "extension");
 
diff --git a/pack-revindex.c b/pack-revindex.c
index 62a9846470c..146334e2c96 100644
--- a/pack-revindex.c
+++ b/pack-revindex.c
@@ -212,7 +212,8 @@ static int load_revindex_from_disk(char *revindex_name,
 	fd = git_open(revindex_name);
 
 	if (fd < 0) {
-		ret = -1;
+		/* "No file" means return 1. */
+		ret = 1;
 		goto cleanup;
 	}
 	if (fstat(fd, &st)) {
@@ -264,7 +265,7 @@ cleanup:
 	return ret;
 }
 
-static int load_pack_revindex_from_disk(struct packed_git *p)
+int load_pack_revindex_from_disk(struct packed_git *p)
 {
 	char *revindex_name;
 	int ret;
diff --git a/pack-revindex.h b/pack-revindex.h
index c8861873b02..6dd47efea10 100644
--- a/pack-revindex.h
+++ b/pack-revindex.h
@@ -51,6 +51,14 @@ struct repository;
  */
 int load_pack_revindex(struct repository *r, struct packed_git *p);
 
+/*
+ * Specifically load a pack revindex from disk.
+ *
+ * Returns 0 on success, 1 on "no .rev file", and -1 when there is an
+ * error parsing the .rev file.
+ */
+int load_pack_revindex_from_disk(struct packed_git *p);
+
 /*
  * verify_pack_revindex verifies that the on-disk rev-index for the given
  * pack-file is the same that would be created if written from scratch.
diff --git a/t/t5325-reverse-index.sh b/t/t5325-reverse-index.sh
index 5c3c80f88f0..431a603ca0e 100755
--- a/t/t5325-reverse-index.sh
+++ b/t/t5325-reverse-index.sh
@@ -190,4 +190,19 @@ test_expect_success 'fsck catches invalid row position' '
 		"invalid rev-index position"
 '
 
+test_expect_success 'fsck catches invalid header: magic number' '
+	corrupt_rev_and_verify 1 "\07" \
+		"reverse-index file .* has unknown signature"
+'
+
+test_expect_success 'fsck catches invalid header: version' '
+	corrupt_rev_and_verify 7 "\02" \
+		"reverse-index file .* has unsupported version"
+'
+
+test_expect_success 'fsck catches invalid header: hash function' '
+	corrupt_rev_and_verify 11 "\03" \
+		"reverse-index file .* has unsupported hash id"
+'
+
 test_done

-- 
gitgitgadget